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

    Neuronpedia

    INDEX
    Explanations

    degrees of strength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    1.29
    다
    1.08
     in
    1.06
    و
    1.04
    า
    0.96
    u
    0.94
    köy
    0.91
    ла
    0.88
    ków
    0.87
    gono
    0.87
    POSITIVE LOGITS
    н
    1.45
    น
    1.34
    ن
    1.21
    न
    1.13
    il
    1.12
    ン
    1.12
     for
    1.11
    。
    1.09
     copi
    1.05
    ز
    1.04
    Act Density 1.327%

    No Known Activations