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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to measurements and variables

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

    Appears after numbers, especially exponents (E) and "years"

    np_acts-logits-general · gemini-2.0-flash

    scientific notation or mixed units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.59
    XmlRootElement
    -0.56
     Numerade
    -0.50
     cherchés
    -0.49
     InputDecoration
    -0.48
     ویکی‌پدی
    -0.47
    typeDefinition
    -0.47
    GEBURTSDATUM
    -0.47
    Билгалдахарш
    -0.46
    لينكات
    -0.45
    POSITIVE LOGITS
     vermelhas
    0.46
    SourceChecksum
    0.40
    <?
    0.40
    cepatan
    0.39
    VersionUID
    0.38
     caminhão
    0.38
    TokenNameCOMMA
    0.38
    ulihan
    0.37
     desempen
    0.36
    oprecipitation
    0.36
    Act Density 0.995%

    No Known Activations