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

    Neuronpedia

    INDEX
    Explanations

    function calls or method invocations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (_)
    1.03
    ("");
    0.96
     ())
    0.96
    ക്കുന്നു
    0.90
    ()["
    0.90
    ("")
    0.88
    ())
    0.86
    ().
    0.86
    ()];
    0.84
    ()]
    0.84
    POSITIVE LOGITS
    ([],
    1.34
    ({},
    1.26
    ('',
    1.20
    ("",
    1.09
    (_,
    1.04
    ('.',
    0.97
    (".",
    0.93
    <(),
    0.90
    ('/',
    0.83
    <{},
    0.81
    Act Density 0.176%

    No Known Activations