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

    Neuronpedia

    INDEX
    Explanations

    introductory markers or section headings in written content

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

    Follows initial punctuation/symbols

    np_acts-logits-general · gemini-2.0-flash

    double d

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.60
     whiteColor
    -0.58
     getUserId
    -0.58
     alertDialog
    -0.57
     numberOf
    -0.56
    ,
    -0.56
     returnValue
    -0.55
    parsedMessage
    -0.55
     totalPrice
    -0.54
     writeTo
    -0.53
    POSITIVE LOGITS
     يتيمه
    0.50
    mtable
    0.48
    ToolStripButton
    0.46
    biendo
    0.45
     linf
    0.43
    ñora
    0.42
    endfor
    0.41
    NÍ
    0.41
    lgari
    0.41
     cible
    0.41
    Act Density 0.622%

    No Known Activations