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

    Neuronpedia

    INDEX
    Explanations

    skills and checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    1.00
    ﺼ
    0.95
    ર
    0.91
    ला
    0.89
    აში
    0.83
    dır
    0.82
    ն
    0.82
    ת
    0.82
    मा
    0.80
    ت
    0.80
    POSITIVE LOGITS
     to
    1.55
    1
    1.16
     on
    1.10
    0
    1.03
     in
    1.02
    <0x0D>
    0.90
    </th>
    0.88
     *
    0.88
     I
    0.87
     or
    0.87
    Act Density 0.000%

    No Known Activations