INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     LOCATION
    -0.08
     retrospect
    -0.08
    -debug
    -0.08
    	entity
    -0.08
    	include
    -0.08
    _serv
    -0.08
     captura
    -0.08
     Euros
    -0.08
    	image
    -0.07
    lights
    -0.07
    POSITIVE LOGITS
     strands
    0.11
     braided
    0.10
     weaving
    0.10
     tubular
    0.09
     permanently
    0.08
     weave
    0.08
    ens
    0.08
     yarn
    0.08
    ENS
    0.08
     crossing
    0.08
    Act Density 0.009%

    No Known Activations