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

    Neuronpedia

    INDEX
    Explanations

    multiple of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ле
    1.35
    ли
    1.29
    تين
    1.08
    ча
    1.06
    تك
    1.05
     (
    1.05
    ющих
    1.02
     on
    1.00
     порядку
    0.99
    lık
    0.98
    POSITIVE LOGITS
    ing
    1.30
    are
    1.26
    ী
    1.19
    io
    1.14
    𝗜
    1.13
     was
    1.06
    uğu
    1.05
    i
    1.02
    am
    0.98
     of
    0.97
    Act Density 0.011%

    No Known Activations