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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement and caution in discussions

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

    proceed with caution, come to mind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     silenzio
    -0.52
     intercambio
    -0.43
    ⎦
    -0.41
     szczegól
    -0.41
    culously
    -0.41
    bulos
    -0.40
     Austausch
    -0.40
     miesięcy
    -0.40
     silencio
    -0.40
     layar
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.56
    DBNull
    0.47
    mergeFrom
    0.46
     كومونز
    0.45
    __(/*!
    0.45
     &___
    0.43
    AutoScaleMode
    0.41
     AssemblyTitle
    0.41
    AlterField
    0.40
     initState
    0.39
    Act Density 0.055%

    No Known Activations