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

    Neuronpedia

    INDEX
    Explanations

    documentation comments and API annotations in code

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

    Text before "@" followed by "return" or "param"

    np_acts-logits-general · gemini-2.0-flash

    code documentation and return types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chré
    -0.59
     الميل
    -0.55
     superficies
    -0.54
    ביוגרפיה
    -0.54
    didSet
    -0.52
     desarrolla
    -0.52
    MeasureSpec
    -0.50
    署
    -0.50
     pelvis
    -0.49
    fillType
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.78
     autorytatywna
    0.77
     ExecuteAsync
    0.65
    EMPL
    0.58
     оригіналу
    0.58
     pylint
    0.57
     محفوظة
    0.57
     InputDecoration
    0.57
     Meksiku
    0.57
    ніципа
    0.57
    Act Density 0.072%

    No Known Activations