INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ك
    0.60
    0.50
    يا
    0.49
    0.47
    ی
    0.47
    نى
    0.44
    ل
    0.43
    ވަ
    0.42
    s
    0.42
    Ý
    0.42
    POSITIVE LOGITS
     Mosque
    0.49
     wedge
    0.45
    Viz
    0.44
     Chirop
    0.44
    Westinghouse
    0.44
     campuran
    0.44
     nuovo
    0.43
     bulge
    0.43
     Pinnacle
    0.43
     Viz
    0.43
    Act Density 0.003%

    No Known Activations