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

    Neuronpedia

    INDEX
    Explanations

    user actions and information processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    1.88
     время
    1.31
    не
    1.23
    ਅ
    1.21
     зависимости
    1.19
    اس
    1.16
    ang
    1.16
    ৪
    1.16
    存档备份
    1.15
    中美
    1.15
    POSITIVE LOGITS
    ों
    1.57
    s
    1.43
    ים
    1.41
    ের
    1.35
    lı
    1.30
    ات
    1.25
    ల్
    1.23
    ς
    1.23
    ın
    1.20
    uff
    1.19
    Act Density 0.190%

    No Known Activations