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 expressions/inequalities

    np_acts-logits-general · gemini-2.0-flash

    mathematical formulas with +

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.69
    Lähteet
    -0.67
    emplares
    -0.59
     ejemplares
    -0.57
     balles
    -0.56
    Przypisy
    -0.56
    Билгалдахарш
    -0.56
     للاسماء
    -0.55
    Források
    -0.55
     mesma
    -0.54
    POSITIVE LOGITS
    /−
    0.80
    ++++++++++++++++
    0.73
    setVerticalGroup
    0.69
    &+
    0.68
    }+\
    0.68
    $+\
    0.67
    ConverterFactory
    0.66
    chitis
    0.64
    ImageContext
    0.63
     مرئيه
    0.63
    Act Density 0.576%

    No Known Activations