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

    Neuronpedia

    INDEX
    Explanations

    references to divine power and the consequences it has on humanity

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

    Follows punctuation/symbols or numbers

    np_acts-logits-general · gemini-2.0-flash

    end-of-sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.60
    CppMethod
    -0.56
    फी
    -0.55
    hasNext
    -0.54
     financières
    -0.53
     OFFERS
    -0.52
    DoubleQuotes
    -0.52
    INER
    -0.52
    Licensed
    -0.51
     arşivlendi
    -0.51
    POSITIVE LOGITS
     SSSR
    0.64
     myſelf
    0.63
     ویکی‌پدیا
    0.59
     pamamagitan
    0.58
     itſelf
    0.57
     uruguay
    0.56
     themſelves
    0.56
    dirond
    0.55
     raiſ
    0.54
     Majefty
    0.54
    Act Density 0.046%

    No Known Activations