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

    Neuronpedia

    INDEX
    Explanations

    ordinal number followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    2.39
    ות
    2.30
     وعلى
    2.00
    ла
    1.97
    ed
    1.91
    uar
    1.89
    ים
    1.81
    );//
    1.80
    ).}
    1.78
    er
    1.77
    POSITIVE LOGITS
    ف
    1.77
    сть
    1.68
    дын
    1.68
    в
    1.68
    ك
    1.68
    ب
    1.66
     lượt
    1.63
    تی
    1.61
     koristiti
    1.61
    ક
    1.59
    Act Density 0.018%

    No Known Activations