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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and syntax

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

    template, macros, and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.74
    ScopeManager
    -0.60
     myſelf
    -0.59
    enumii
    -0.57
    ruptedException
    -0.57
    lesias
    -0.57
    +#+#
    -0.56
    Билгалдахарш
    -0.56
    Autoritní
    -0.56
    OCCURRED
    -0.54
    POSITIVE LOGITS
     Мексичка
    0.33
     wynika
    0.32
    UNGEN
    0.30
     maximal
    0.30
     diny
    0.29
    ทะ
    0.29
    помним
    0.29
    constexpr
    0.29
    rost
    0.28
    lığ
    0.28
    Act Density 0.283%

    No Known Activations