INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     curled
    0.44
    BoolVar
    0.41
     ojos
    0.40
     marbled
    0.38
    قيقة
    0.37
     ohmic
    0.37
     riser
    0.37
    SCUS
    0.37
    whis
    0.36
     manquer
    0.36
    POSITIVE LOGITS
     Components
    0.81
     components
    0.77
     componentes
    0.76
     UI
    0.75
    Components
    0.74
     компонен
    0.71
     компонентов
    0.71
     MUI
    0.70
    components
    0.69
     MU
    0.64
    Act Density 0.004%

    No Known Activations