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

    Neuronpedia

    INDEX
    Explanations

    boolean values or indicators of truth in the context of programming or logic

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

    false answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.79
     surla
    -0.73
    transQ
    -0.71
    expandindo
    -0.70
     للاسماء
    -0.59
    -0.57
    TokenNameDOT
    -0.56
     الحره
    -0.56
     EconPapers
    -0.56
     wireType
    -0.55
    POSITIVE LOGITS
    :✨
    0.41
    endpush
    0.39
    UNIDENTIFIED
    0.29
     mentes
    0.28
    RESUMO
    0.27
     autorytatywna
    0.26
    EndInit
    0.26
    チール
    0.26
    puestas
    0.26
    SuspendLayout
    0.26
    Act Density 0.000%

    No Known Activations