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

    Neuronpedia

    INDEX
    Explanations

    limited quantities or maximums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    timer
    0.38
    ૃહ
    0.37
     dominates
    0.36
     concaten
    0.36
    කිය
    0.36
    丰富的
    0.36
    វែង
    0.36
     आर्
    0.35
     doma
    0.35
    深的
    0.34
    POSITIVE LOGITS
     تعداد
    0.65
     सीमित
    0.63
    人数
    0.62
     limited
    0.61
     সংখ্যক
    0.59
     количеством
    0.59
    數量
    0.58
     limitada
    0.57
    数量
    0.57
     محدود
    0.57
    Act Density 0.063%

    No Known Activations