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

    Neuronpedia

    INDEX
    Explanations

    Chinese language listings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    سر
    1.08
    л
    1.03
    تي
    1.02
     composés
    1.01
    ס
    1.00
    س
    0.91
    تد
    0.89
    ıları
    0.88
     интерес
    0.88
     geométricas
    0.88
    POSITIVE LOGITS
    w
    1.33
    1
    1.31
     I
    1.25
     China
    1.17
    China
    1.16
    an
    1.13
    CHINA
    1.13
    ១
    1.12
     中国
    1.11
    a
    1.08
    Act Density 0.024%

    No Known Activations