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

    Neuronpedia

    INDEX
    Explanations

    AI related acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     construire
    0.82
    べく
    0.79
    يا
    0.76
     вертика
    0.75
     awfully
    0.75
    сть
    0.75
    Ве
    0.75
    ਕੇ
    0.74
    يمة
    0.74
    Тер
    0.73
    POSITIVE LOGITS
    ik
    0.88
    น
    0.84
    lk
    0.77
    ่
    0.76
    ñas
    0.76
    id
    0.74
     Recognize
    0.74
    n
    0.73
     uključ
    0.71
    lion
    0.71
    Act Density 0.013%

    No Known Activations