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

    Neuronpedia

    INDEX
    Explanations

    freedom to create own meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    況
    0.44
    QLabel
    0.43
    abbati
    0.42
    顧客
    0.41
    退出
    0.40
    त्मक
    0.39
    新しい
    0.39
     buyers
    0.38
     embers
    0.38
     عورت
    0.38
    POSITIVE LOGITS
     স্বাধীন
    0.44
     junio
    0.44
     indépend
    0.44
    ค่อย
    0.42
    전
    0.42
     birthdays
    0.41
     başlayalım
    0.40
    Free
    0.40
    વ
    0.40
     Free
    0.39
    Act Density 0.003%

    No Known Activations