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

    Neuronpedia

    INDEX
    Explanations

    time duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     year
    0.59
     yearly
    0.58
     aast
    0.58
     annually
    0.58
     annual
    0.54
     Jahres
    0.53
     año
    0.52
     yıl
    0.52
     tahun
    0.52
     scars
    0.52
    POSITIVE LOGITS
     momentarily
    0.65
     কিছুক্ষণ
    0.63
    休憩
    0.63
     मिनट
    0.59
     minutos
    0.58
     mentre
    0.58
    minutes
    0.57
     минут
    0.57
    会儿
    0.57
    手机
    0.55
    Act Density 0.093%

    No Known Activations