Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts

• URL: http://arxiv.org/abs/2605.24846v2
• Date: Wed, 27 May 2026 17:45:10 GMT
• Title: Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts
• Abstract summary: We show that across a wide range of open-weight Transformers, a subset of neurons remains consistently highly activated during inference across tasks of multiple capability dimensions.<n>By probing along the cross-task activation strength, an extremely sparse subset is isolated, whose removal causes a collapse in model behavior.<n>Our analysis reveals that keystone neurons are a stable and intrinsic neuron subset of the model that is largely established during pretraining.
• Score: 57.98275914877019
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms that support these behaviors remain insufficiently understood. In this work, we show that across a wide range of open-weight Transformers, a subset of neurons remains consistently highly activated during inference across tasks of multiple capability dimensions. By probing along the cross-task activation strength, an extremely sparse subset is isolated, whose removal causes a collapse in model behavior, which we term keystone neurons. Our analysis reveals that keystone neurons are a stable and intrinsic neuron subset of the model that is largely established during pretraining. The parameters associated with these neurons are tightly calibrated during the training process, and their precise values are critical for the capabilities of the model. Building on these insights, we propose a supervised fine-tuning approach that updates only keystone neurons, achieving task gains comparable to or even better than full-parameter fine-tuning while better preserving performance in other capability dimensions, despite modifying a much smaller number of parameters.

Related papers

• Selective Neuron Amplification for Training-Free Task Enhancement [0.0]
  Selective Neuron Amplification increases the influence of task relevant neurons without changing the model's parameters.<n>This suggests that some model failures are due to weak activation rather than lack of capability.
  arXiv  Detail & Related papers  (2026-04-08T13:51:07Z)
• Neuronal Group Communication for Efficient Neural representation [85.36421257648294]
  This paper addresses the question of how to build large neural systems that learn efficient, modular, and interpretable representations.<n>We propose Neuronal Group Communication (NGC), a theory-driven framework that reimagines a neural network as a dynamical system of interacting neuronal groups.<n>NGC treats weights as transient interactions between embedding-like neuronal states, with neural computation unfolding through iterative communication among groups of neurons.
  arXiv  Detail & Related papers  (2025-10-19T14:23:35Z)
• NOBLE -- Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models [63.592664795493725]
  NOBLE is a neural operator framework that learns a mapping from a continuous frequency-modulated embedding of interpretable neuron features to the somatic voltage response induced by current injection.<n>It predicts distributions of neural dynamics accounting for the intrinsic experimental variability.<n>NOBLE is the first scaled-up deep learning framework that validates its generalization with real experimental data.
  arXiv  Detail & Related papers  (2025-06-05T01:01:18Z)
• To See a World in a Spark of Neuron: Disentangling Multi-task Interference for Training-free Model Merging [16.81093103067372]
  We present the first study that relies on neuronal mechanisms for model merging.<n>We introduce NeuroMerging, a novel merging framework developed to mitigate task interference within neuronal subspaces.<n>Our findings highlighted the importance of aligning neuronal mechanisms in model merging.
  arXiv  Detail & Related papers  (2025-03-07T11:00:24Z)
• Let's Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model [43.107778640669544]
  Large Language Models (LLMs) are composed of neurons that exhibit various behaviors and roles. Recent studies have revealed that not all neurons are active across different datasets. We introduce Neuron-Level Fine-Tuning (NeFT), a novel approach that refines the granularity of parameter training down to the individual neuron.
  arXiv  Detail & Related papers  (2024-03-18T09:55:01Z)
• Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data [3.46029409929709]
  State-of-the-art systems neuroscience experiments yield large-scale multimodal data, and these data sets require new tools for analysis. Inspired by the success of large pretrained models in vision and language domains, we reframe the analysis of large-scale, cellular-resolution neuronal spiking data into an autoregressive generation problem. We first trained Neuroformer on simulated datasets, and found that it both accurately predicted intrinsically simulated neuronal circuit activity, and also inferred the underlying neural circuit connectivity, including direction.
  arXiv  Detail & Related papers  (2023-10-31T20:17:32Z)
• The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks [64.08042492426992]
  We introduce the Expressive Memory (ELM) neuron model, a biologically inspired model of a cortical neuron. Our ELM neuron can accurately match the aforementioned input-output relationship with under ten thousand trainable parameters. We evaluate it on various tasks with demanding temporal structures, including the Long Range Arena (LRA) datasets.
  arXiv  Detail & Related papers  (2023-06-14T13:34:13Z)
• To update or not to update? Neurons at equilibrium in deep models [8.72305226979945]
  Recent advances in deep learning showed that, with some a-posteriori information on fully-trained models, it is possible to match the same performance by simply training a subset of their parameters. In this work we shift our focus from the single parameters to the behavior of the whole neuron, exploiting the concept of neuronal equilibrium (NEq) The proposed approach has been tested on different state-of-the-art learning strategies and tasks, validating NEq and observing that the neuronal equilibrium depends on the specific learning setup.
  arXiv  Detail & Related papers  (2022-07-19T08:07:53Z)
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks [68.8204255655161]
  Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks. We explore the diversity of the neurons within the hidden layer during the learning process. We analyze how the diversity of the neurons affects predictions of the model.
  arXiv  Detail & Related papers  (2021-09-20T15:12:16Z)
• Continuous Learning and Adaptation with Membrane Potential and Activation Threshold Homeostasis [91.3755431537592]
  This paper presents the Membrane Potential and Activation Threshold Homeostasis (MPATH) neuron model. The model allows neurons to maintain a form of dynamic equilibrium by automatically regulating their activity when presented with input. Experiments demonstrate the model's ability to adapt to and continually learn from its input.
  arXiv  Detail & Related papers  (2021-04-22T04:01:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.