Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sections or descriptors indicating an overview or summary in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    overview of a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jewish
    -0.47
    cobacterium
    -0.46
    Machine
    -0.45
    
    -0.45
    SqlClient
    -0.44
    */].
    -0.43
    Japanese
    -0.41
    jsonwebtoken
    -0.41
    Belgian
    -0.40
    stridium
    -0.40
    POSITIVE LOGITS
     overview
    1.40
     Overview
    1.30
    overview
    1.21
    Overview
    1.20
     OVERVIEW
    1.09
    OVERVIEW
    1.06
     Überblick
    1.04
     summary
    0.95
     Übersicht
    0.95
     概要
    0.85
    Act Density 0.004%

    No Known Activations