INDEX
    Explanations

    The neuron fires on numeric CSS property values (e.g. “0”, “fixed”, “auto” values in style declarations).

    New Auto-Interp
    Negative Logits
    owards
    -0.07
    रत
    -0.07
    oris
    -0.07
    employee
    -0.06
     Dog
    -0.06
    -of
    -0.06
    my
    -0.06
    .tb
    -0.06
    partial
    -0.06
    government
    -0.06
    POSITIVE LOGITS
    ();
    0.08
     define
    0.08
    ");
    0.08
     );
    0.07
    ');
    0.07
     "");
    0.07
     handlers
    0.07
     player
    0.07
    );
    0.07
     };
    0.07
    Act Density 0.017%

    No Known Activations