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

    Neuronpedia

    INDEX
    Explanations

    error messages and warning statements in code

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

    ignore or warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.41
     gainera
    -0.39
     Geb
    -0.38
    mergeFrom
    -0.37
    Tikang
    -0.36
     Exactos
    -0.36
     sud
    -0.35
    PMailer
    -0.33
    Hentet
    -0.33
    AxisAlignment
    -0.33
    POSITIVE LOGITS
     CanadaChoose
    0.50
     مشين
    0.47
    şört
    0.46
    éfono
    0.46
    enterian
    0.44
    Попис
    0.44
    ună
    0.44
    0.43
     onFailure
    0.43
     ModelExpression
    0.43
    Act Density 0.073%

    No Known Activations