Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emuls
    0.61
     not
    0.60
     inhaled
    0.60
    ,
    0.60
     we
    0.58
     diluted
    0.58
     don
    0.57
     no
    0.55
     you
    0.55
     touchdown
    0.55
    POSITIVE LOGITS
    ())
    0.90
    ()).
    0.89
    ("
    0.88
    ();
    0.86
    ().
    0.85
    ("",
    0.84
    (`${
    0.83
    ());
    0.81
    ()
    0.80
    ()}
    0.80
    Act Density 0.477%

    No Known Activations