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

    Neuronpedia

    INDEX
    Explanations

    intensifiers and expressions of enthusiasm or emphasis

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

    "Really" as an intensifier

    np_acts-logits-general · gemini-2.0-flash

    intensifier for emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اتي
    -0.61
    formik
    -0.61
     "'",
    -0.61
     Wiseman
    -0.61
    니다
    -0.60
     Shades
    -0.59
    Datuak
    -0.58
    Shades
    -0.58
     linkovi
    -0.58
     automáticamente
    -0.55
    POSITIVE LOGITS
     REALLY
    0.87
     really
    0.80
     realy
    0.78
    really
    0.78
    mergeFrom
    0.74
     Really
    0.68
    benar
    0.66
     quite
    0.66
    ibatis
    0.65
    ngOnInit
    0.63
    Act Density 0.073%

    No Known Activations