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

    Neuronpedia

    INDEX
    Explanations

    function definitions and method calls in code

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

    programming code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.91
    Tembelea
    -0.77
    Искәрмәләр
    -0.75
    хьтан
    -0.72
     surla
    -0.69
    UserScript
    -0.69
    httphttps
    -0.67
     Мексичка
    -0.67
    AISSEE
    -0.66
    principalColumn
    -0.65
    POSITIVE LOGITS
     estructural
    0.38
     conmigo
    0.35
     viñ
    0.32
     également
    0.31
     bref
    0.30
     atve
    0.30
     szint
    0.30
    ducir
    0.29
    ormais
    0.29
     aporte
    0.29
    Act Density 0.003%

    No Known Activations