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

    Neuronpedia

    INDEX
    Explanations

    markdown and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (_)
    0.98
     {}'.
    0.96
     ())
    0.92
    ("");
    0.91
    ()
    0.90
    ();
    0.88
     {}".
    0.84
     ()
    0.82
    ('');
    0.82
    ക്കുന്നു
    0.81
    POSITIVE LOGITS
    ([],
    1.52
    ({},
    1.52
    ("",
    1.35
    ('',
    1.35
    (_,
    1.25
    <{},
    1.21
    ('/',
    1.05
    ("/",
    1.02
    <(),
    1.01
    (".",
    0.94
    Act Density 0.380%

    No Known Activations