INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    面积
    -0.10
    -0.08
    规模
    -0.08
     traslad
    -0.08
     Area
    -0.08
     ночью
    -0.07
     Tir
    -0.07
     क्षेत्र
    -0.07
    area
    -0.07
    _area
    -0.07
    POSITIVE LOGITS
     woven
    0.11
     fabric
    0.09
     Bestandteil
    0.09
     fabrics
    0.08
     tapestry
    0.08
     tissu
    0.08
     tecido
    0.08
     برخ
    0.08
     seemingly
    0.08
    kw
    0.08
    Act Density 0.008%

    No Known Activations