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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "say" and its variations along with expressions indicating speech or communication

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

    I say that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.55
    पया
    -0.46
     sub
    -0.43
    ódó
    -0.43
    お世話
    -0.42
    ἶ
    -0.41
    Кан
    -0.40
    bureau
    -0.39
     graag
    -0.39
     كومونز
    -0.39
    POSITIVE LOGITS
    +#+
    0.52
    enumi
    0.47
    MessageOf
    0.45
    EndInit
    0.44
    typeorm
    0.41
    出版年
    0.40
     męska
    0.39
    GEBURTSDATUM
    0.38
     say
    0.38
    addGap
    0.37
    Act Density 0.021%

    No Known Activations