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

    Neuronpedia

    INDEX
    Explanations

    express initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    佃
    0.43
     اط
    0.42
     انت
    0.41
    :*
    0.41
     अध
    0.40
     اث
    0.39
    зина
    0.39
     தி
    0.39
     સો
    0.38
    اح
    0.38
    POSITIVE LOGITS
    ។
    0.50
     ঝড়
    0.47
    s
    0.46
    ים
    0.46
     retirada
    0.45
    ่า
    0.44
    ی
    0.41
    ప్రదేశ్
    0.41
     методом
    0.41
     репре
    0.40
    Act Density 0.002%

    No Known Activations