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

    Neuronpedia

    INDEX
    Explanations

    Master's degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ج
    1.55
    ت
    1.30
    ب
    1.28
    ك
    1.23
    ak
    1.23
    is
    1.22
    ا
    1.20
    א
    1.19
    اك
    1.18
    ع
    1.18
    POSITIVE LOGITS
    ур
    0.77
     rotational
    0.73
     conclusive
    0.69
    یکس
    0.67
     in
    0.66
    ння
    0.66
    r
    0.66
     capability
    0.65
    적인
    0.65
     revolutionary
    0.65
    Act Density 0.021%

    No Known Activations