INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     patrim
    -0.08
     வாழ
    -0.08
     ange
    -0.08
     Hug
    -0.07
     native
    -0.07
     biodiversity
    -0.07
    pag
    -0.07
     സ്വദേശ
    -0.07
     Apartment
    -0.07
     Ecos
    -0.07
    POSITIVE LOGITS
    0.09
    formal
    0.08
     stalls
    0.08
    II
    0.08
     formal
    0.08
     Formal
    0.08
    YD
    0.08
    డు
    0.07
    EI
    0.07
    IL
    0.07
    Act Density 0.001%

    No Known Activations