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

    Neuronpedia

    INDEX
    Explanations

    programming-related constructs and logical structures

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

    whereas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monks
    -0.36
    yntaxException
    -0.35
     Morm
    -0.35
    abank
    -0.34
     Citron
    -0.32
    retirement
    -0.32
    RTLD
    -0.32
    ۣ
    -0.32
     cic
    -0.32
     prospec
    -0.31
    POSITIVE LOGITS
    dafx
    0.60
     gambe
    0.56
     تضيفلها
    0.56
    awtextra
    0.56
    disposing
    0.52
     оригіналу
    0.50
    Бахар
    0.50
     misure
    0.49
     للاسماء
    0.49
     ویکی‌آمباردا
    0.48
    Act Density 0.170%

    No Known Activations