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

    Neuronpedia

    INDEX
    Explanations

    mathematical and statistical terms or symbols in the context of research data

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

    Prepositions followed by comparatives

    np_acts-logits-general · gemini-2.0-flash

    percentages and comparatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.82
     مشين
    -0.77
    存于互联网档案馆
    -0.73
     Савезне
    -0.70
     referrerpolicy
    -0.68
     useStyles
    -0.67
     isNameExpr
    -0.64
    <?
    -0.64
     ویکی‌پدیای
    -0.63
     كومونز
    -0.63
    POSITIVE LOGITS
     
    2.15
     $
    0.54
     ২
    0.44
    ktır
    0.43
    ()]);
    0.42
    acakt
    0.41
     ১
    0.40
    wikk
    0.39
    ]');
    0.39
     fous
    0.39
    Act Density 2.925%

    No Known Activations