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

    Neuronpedia

    INDEX
    Explanations

    key phrases indicating legal arguments and assertions

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

    legal arguments and evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.36
    薙
    -0.34
    })->
    -0.34
     Specification
    -0.33
    olverine
    -0.32
    日報
    -0.31
     sujetos
    -0.30
     sulit
    -0.30
    Specification
    -0.30
     venons
    -0.30
    POSITIVE LOGITS
     للاسماء
    0.60
    tonode
    0.59
     autorytatywna
    0.57
    setupUi
    0.55
    adaptiveStyles
    0.54
    saraba
    0.52
    setVerticalGroup
    0.52
     ब्रेकडाउन
    0.52
     المعيارى
    0.51
    :✨
    0.50
    Act Density 0.158%

    No Known Activations