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

    Neuronpedia

    INDEX
    Explanations

    Follow simple ingenuity signing rise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ような
    0.72
    ธาน
    0.61
    Downloaded
    0.60
     dow
    0.59
     nhiệm
    0.57
    ✕
    0.57
    hills
    0.56
     distilled
    0.56
    truth
    0.55
    ➢
    0.55
    POSITIVE LOGITS
    rhs
    0.80
     komma
    0.79
     والصلاه
    0.79
    origine
    0.79
    рому
    0.78
    <unused1821>
    0.78
    ൭
    0.77
     kirj
    0.76
     komme
    0.75
    aske
    0.75
    Act Density 0.000%

    No Known Activations