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

    Neuronpedia

    INDEX
    Explanations

    Monte Carlo simulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ล
    1.07
    (
    1.00
    ल
    0.99
    ش
    0.97
    -
    0.93
    lø
    0.88
    ק
    0.86
    س
    0.85
    ز
    0.83
    '
    0.77
    POSITIVE LOGITS
     ホーム
    0.84
     나
    0.81
     ઉ
    0.76
     Как
    0.72
     сообщения
    0.72
     这里
    0.71
     Swindon
    0.71
     మీరు
    0.70
     Sutter
    0.69
     这
    0.68
    Act Density 0.001%

    No Known Activations