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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

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

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Neighbors
    -0.38
    inafter
    -0.37
    garmin
    -0.36
    labeling
    -0.35
    Spa
    -0.34
    mitian
    -0.34
     ainfi
    -0.34
     vocês
    -0.33
    IpAddress
    -0.33
     Spa
    -0.33
    POSITIVE LOGITS
    脚注の使い方
    0.62
    AndEndTag
    0.59
     ویکی‌پدی
    0.59
    évaluateur
    0.56
     INTERESAR
    0.56
     Comprometido
    0.55
     ब्रेकडाउन
    0.54
    UrlResolution
    0.52
     Numerade
    0.52
    RenderAtEndOf
    0.52
    Act Density 3.358%

    No Known Activations