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

    Neuronpedia

    INDEX
    Explanations

    technical or programming-related terminology and function calls

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

    Word followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    describing quantities or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.53
    ge
    -0.49
    t
    -0.45
    n
    -0.45
    æ
    -0.43
    э
    -0.43
    w
    -0.43
    le
    -0.43
    f
    -0.42
    wat
    -0.42
    POSITIVE LOGITS
    ########.
    1.36
     تضيفلها
    1.27
    Personensuche
    1.23
     Wikimedijinoj
    1.09
     ExecuteAsync
    1.05
    SharedCtor
    1.01
    expandindo
    1.00
    aarrggbb
    1.00
     مشين
    1.00
     Мексичка
    0.99
    Act Density 1.185%

    No Known Activations