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

    Neuronpedia

    INDEX
    Explanations

    expressions related to uncertainty and inquiry

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

    Comes before "whether" or "how"

    np_acts-logits-general · gemini-2.0-flash

    explores whether or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.51
     Rodrig
    -0.38
    colla
    -0.35
    closeConnection
    -0.35
    Reminds
    -0.34
     Greet
    -0.34
    antası
    -0.33
     ADC
    -0.33
     Replaced
    -0.32
    新た
    -0.32
    POSITIVE LOGITS
    GraphicsUnit
    0.55
    addCriterion
    0.49
     Wikimedijinoj
    0.48
     مشارکت‌کنندگان
    0.48
     WaitForSeconds
    0.47
    wnież
    0.47
     CallOverrides
    0.47
    berdayakan
    0.47
    enumi
    0.47
    出版年
    0.47
    Act Density 0.389%

    No Known Activations