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

    Neuronpedia

    INDEX
    Explanations

    finding information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    1.11
    ，
    1.06
    ким
    1.03
    نت
    1.02
    ني
    1.01
    мих
    0.98
    났
    0.97
    Benzoimidazol
    0.96
    حه
    0.95
    mobilpay
    0.94
    POSITIVE LOGITS
    g
    1.57
    し
    1.45
    ada
    1.32
    ان
    1.27
    an
    1.24
    iv
    1.20
    r
    1.19
    n
    1.18
    j
    1.18
    ul
    1.15
    Act Density 0.002%

    No Known Activations