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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and identifiers related to scientific and mathematical concepts

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

    or characters preceding citations

    np_acts-logits-general · gemini-2.0-flash

    mathematical/scientific abbreviations and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sweise
    -0.88
    ième
    -0.79
     Administrativna
    -0.77
     Grüsse
    -0.71
     miniaturka
    -0.70
    iyle
    -0.67
    ۰
    -0.66
    ు
    -0.65
     zijne
    -0.64
    ی
    -0.64
    POSITIVE LOGITS
    <bos>
    2.17
    yszer
    0.71
    してみて
    0.68
    ítmény
    0.63
    ってみて
    0.61
    vény
    0.60
    çası
    0.60
    hamm
    0.58
    mens
    0.57
    himo
    0.57
    Act Density 2.909%

    No Known Activations