INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     metal
    -0.07
     barbar
    -0.07
     Hob
    -0.07
    _ul
    -0.07
     Vent
    -0.06
    -guid
    -0.06
     bul
    -0.06
     lif
    -0.06
    BLACK
    -0.06
     Mut
    -0.06
    POSITIVE LOGITS
    	Schema
    0.07
    aravel
    0.07
     yüksel
    0.07
     };↵
    0.06
     professors
    0.06
    rending
    0.06
     PropertyValue
    0.06
     scaleX
    0.06
     Georgia
    0.06
    iktig
    0.06
    Act Density 0.010%

    No Known Activations