LINE: LLM-based Iterative Neuron Explanations for Vision Models

arXiv:2604.08039v2 Announce Type: replace-cross Abstract: Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the search space to predefined concept vocabularies or produce overly specific descriptions that fail to capture higher-order, global concepts. We introduce LINE, a novel, training-free iterative approach tail