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

    Neuronpedia

    INDEX
    Explanations

    name of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.80
    ت
    0.80
    ب
    0.80
     valores
    0.74
     зрения
    0.72
     residuos
    0.72
     clín
    0.70
     gái
    0.69
     número
    0.68
     deseos
    0.66
    POSITIVE LOGITS
    names
    0.85
    akes
    0.82
    ни
    0.78
    clature
    0.78
    ชื่อ
    0.77
    ه‌ها
    0.77
    ناسب
    0.76
    ורי
    0.75
    کن
    0.73
    करण
    0.73
    Act Density 0.105%

    No Known Activations