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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation related to code syntax

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

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pnt
    -0.36
    togg
    -0.32
     которое
    -0.32
     itself
    -0.32
     Principle
    -0.29
     principle
    -0.28
     Itself
    -0.27
     child
    -0.27
     ребен
    -0.27
    findpost
    -0.27
    POSITIVE LOGITS
    InitVars
    0.79
    ühungen
    0.73
    ViewFeatures
    0.68
    ergies
    0.64
     generalizations
    0.64
     lesbians
    0.64
    letons
    0.63
    assies
    0.63
     abstractions
    0.63
    crapers
    0.63
    Act Density 0.616%

    No Known Activations