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

    Neuronpedia

    INDEX
    Explanations

    time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ار
    1.01
    اول
    0.95
    ется
    0.94
    ة
    0.91
    াল
    0.89
    ا
    0.88
    وون
    0.88
    ל
    0.87
    ع
    0.86
    ЗА
    0.86
    POSITIVE LOGITS
     Wechsler
    0.80
    OO
    0.77
     (
    0.76
     อืม
    0.76
    (
    0.74
    Relax
    0.72
    EM
    0.71
     ประจํา
    0.71
    BS
    0.70
    .
    0.70
    Act Density 0.065%

    No Known Activations