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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific numeric values or related parameters in programming contexts

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

    return value from function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.56
     BoxDecoration
    -0.54
    QRect
    -0.53
    jgl
    -0.52
    RotationOrder
    -0.52
    dafx
    -0.49
     ſur
    -0.49
    ConstraintMaker
    -0.49
     puro
    -0.49
     viſ
    -0.48
    POSITIVE LOGITS
    ----------------
    0.45
     للمعارف
    0.45
    dienne
    0.44
    érience
    0.39
     suspiciously
    0.38
    OVERR
    0.38
     prioritize
    0.38
    DISABLED
    0.37
     Référence
    0.37
    spě
    0.36
    Act Density 0.016%

    No Known Activations