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

    Neuronpedia

    INDEX
    Explanations

    performance and biology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تین
    0.42
    不仅仅
    0.42
    с
    0.42
     này
    0.40
     Хо
    0.40
    ۔
    0.40
    的
    0.39
    ス
    0.39
     Герма
    0.39
    ው
    0.39
    POSITIVE LOGITS
     a
    0.50
     A
    0.44
    ad
    0.44
    ir
    0.44
    า
    0.44
    A
    0.42
    א
    0.41
    ัน
    0.41
     M
    0.40
    f
    0.40
    Act Density 7.606%

    No Known Activations