AI RESEARCH
What is Missing? Explaining Neurons Activated by Absent Concepts
arXiv CS.LG
•
ArXi:2603.09787v1 Announce Type: cross Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically by estimating a simplified causal structure of the model. In existing work, this causal structure often includes relationships where the presence of a concept is associated with a strong activation of a neuron.