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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numeric values or identifiers associated with labels

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

    coordinates and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astéroïdes
    -0.54
    awtextra
    -0.46
    IntentFilter
    -0.43
     typelib
    -0.42
    transQ
    -0.41
     canon
    -0.40
    LayoutConstraint
    -0.37
    AccessorTable
    -0.37
    setViewportView
    -0.37
    MeasureSpec
    -0.37
    POSITIVE LOGITS
    הערות
    0.54
    sidemargin
    0.49
     susun
    0.47
     autorytatywna
    0.47
     Autorisations
    0.43
    ⓧ
    0.43
     ProtoMessage
    0.42
    impianto
    0.41
    DoubleQuotes
    0.41
    gæ
    0.41
    Act Density 0.021%

    No Known Activations