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

Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts arXiv:2605.24846v1 Announce Type: cross 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.