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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ຜູ້
    0.41
     Taft
    0.39
    Rooms
    0.38
    숙
    0.38
     Thread
    0.37
     σκ
    0.37
     Cev
    0.37
     Arr
    0.37
     Cuy
    0.37
    摇
    0.37
    POSITIVE LOGITS
    ề
    0.44
     اقتصادی
    0.43
    コスト
    0.42
     економі
    0.42
     calmed
    0.41
     ಮಹಿ
    0.41
     anticoagulant
    0.41
    鞏
    0.41
     文
    0.40
    キャリア
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.