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

    Neuronpedia

    INDEX
    Explanations

    of a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.04
    z
    0.84
    و
    0.74
    g
    0.71
    in
    0.70
    xiety
    0.67
    about
    0.65
    ୍ର
    0.65
    gressive
    0.65
    folding
    0.64
    POSITIVE LOGITS
    ון
    0.84
    Рис
    0.81
    ة
    0.78
    Url
    0.74
    หรือไม่
    0.73
    Width
    0.73
    Insight
    0.73
     เจอ
    0.71
    ों
    0.71
    ต์
    0.71
    Act Density 0.574%

    No Known Activations