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

    Neuronpedia

    INDEX
    Explanations

    function definitions in coding contexts

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

    function followed by parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OrBuilder
    -0.47
    Personensuche
    -0.47
     nakalista
    -0.44
     autorytatywna
    -0.42
    TintMode
    -0.42
    évaluateur
    -0.42
    TypedDataSet
    -0.41
     tiguan
    -0.41
     समीक्षक
    -0.40
    Portail
    -0.39
    POSITIVE LOGITS
    inSlope
    0.46
     yhte
    0.42
     ancestor
    0.41
    guns
    0.40
    matica
    0.40
     guns
    0.40
    internal
    0.39
    мето
    0.39
    MethodImpl
    0.39
     Santi
    0.39
    Act Density 0.179%

    No Known Activations