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

    Neuronpedia

    INDEX
    Explanations

    /n sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    1.00
    い
    0.90
    ی
    0.86
    0
    0.79
    其他
    0.72
    s
    0.71
    ים
    0.71
     (
    0.66
    ات
    0.64
    <0x80>
    0.64
    POSITIVE LOGITS
    the
    0.81
    erv
    0.79
    ral
    0.73
    ermost
    0.72
    etheless
    0.68
    ра
    0.67
    ला
    0.67
    ale
    0.66
    amb
    0.66
     terug
    0.66
    Act Density 0.000%

    No Known Activations