INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    oviruses
    0.34
     dehuman
    0.33
     인식
    0.31
     کمپیوٹر
    0.31
     xbox
    0.30
    দ্বন্দ্ব
    0.30
     apathy
    0.30
    分裂
    0.30
    Convolution
    0.30
     suicide
    0.30
    POSITIVE LOGITS
     cuisine
    0.82
     restaurant
    0.80
     ресторан
    0.79
     yemek
    0.75
     culinary
    0.75
     comida
    0.74
    美食
    0.74
     ristorante
    0.74
     Restaurant
    0.73
     gastronom
    0.73
    Act Density 0.161%

    No Known Activations