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

    Neuronpedia

    INDEX
    Explanations

    from datetime import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.86
    ल
    0.86
    ले
    0.77
    ,
    0.76
    ش
    0.76
    ला
    0.68
    도
    0.66
    त
    0.66
    ব
    0.66
    、
    0.66
    POSITIVE LOGITS
    uje
    0.68
    ０
    0.66
    제곱
    0.65
    atok
    0.64
    a
    0.64
     ဆ
    0.64
     A
    0.61
    ươ
    0.61
    aabb
    0.61
     ដ
    0.61
    Act Density 0.010%

    No Known Activations