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

    Neuronpedia

    INDEX
    Explanations

    coming down, dashboard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.46
     כל
    0.46
     রক্ত
    0.45
     ທ
    0.45
     ফলাফল
    0.45
     ဗ
    0.44
    ());
    0.43
     απα
    0.43
     પ્ર
    0.43
    」。
    0.43
    POSITIVE LOGITS
    P
    0.56
    ن
    0.55
     Foxes
    0.51
     edged
    0.50
    G
    0.50
     Betfair
    0.48
    S
    0.48
    <blockquote>
    0.47
    ات
    0.47
    Ripe
    0.47
    Act Density 0.000%

    No Known Activations