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

    Neuronpedia

    INDEX
    Explanations

    protective sleeve or covering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.88
    ta
    0.79
    ları
    0.79
    1
    0.79
    ın
    0.79
    2
    0.77
    ;
    0.77
    r
    0.75
    n
    0.74
    ned
    0.73
    POSITIVE LOGITS
    ح
    0.79
    로운
    0.73
    也
    0.73
    స్‌
    0.71
     الفرنس
    0.70
    ంక
    0.69
     اين
    0.69
    M
    0.68
    TION
    0.68
    ستي
    0.68
    Act Density 0.001%

    No Known Activations