INDEX
    Explanations

    This neuron detects the word “adult” (as in references to an adult menu or adult portion).

    New Auto-Interp
    Negative Logits
     borders
    -0.07
     Notifications
    -0.06
     Gew
    -0.06
     уда
    -0.06
     Toast
    -0.06
     high
    -0.06
     exiting
    -0.06
     charming
    -0.06
     изменения
    -0.06
     کش
    -0.06
    POSITIVE LOGITS
    ');?>↵
    0.07
    urities
    0.06
     переш
    0.06
     ArgumentException
    0.06
     TRANSACTION
    0.06
    	be
    0.06
     घर
    0.06
    ="'+
    0.06
     RG
    0.06
    ".$
    0.06
    Act Density 0.082%

    No Known Activations