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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to class definitions and utilities in code

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

    class and Utils test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.67
    complexContent
    -0.64
     autorytatywna
    -0.62
    EDEFAULT
    -0.60
    ftagPool
    -0.59
    EndContext
    -0.58
     onCancelled
    -0.56
    ConstraintMaker
    -0.55
    saraba
    -0.54
    twimg
    -0.53
    POSITIVE LOGITS
     unum
    0.35
    }{*}{}
    0.33
    OrderService
    0.32
    DropDown
    0.31
    inko
    0.29
    īgā
    0.28
    ille
    0.28
    ierend
    0.28
    akaian
    0.28
    file
    0.27
    Act Density 0.197%

    No Known Activations