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

    Neuronpedia

    INDEX
    Explanations

    function call syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wisdom
    0.89
     te
    0.85
     folk
    0.82
     rose
    0.82
     interspersed
    0.80
     Aaron
    0.80
     deemed
    0.79
     intertwined
    0.79
     intertw
    0.78
     interwoven
    0.78
    POSITIVE LOGITS
    ("
    2.22
    ((
    2.17
    (
    2.11
    ()
    2.06
    ('
    2.00
    ();
    1.99
    ())
    1.93
    ());
    1.83
    ("")
    1.80
    (\
    1.77
    Act Density 0.641%

    No Known Activations