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

    Neuronpedia

    INDEX
    Explanations

    programming math and utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Elektrokhimiya
    0.42
    =\{\
    0.40
     Solubility
    0.38
    <unused262>
    0.38
    }=\{\
    0.37
     ऑर्गे
    0.37
    fired
    0.36
     त्वचा
    0.35
     निधी
    0.35
     সরবরাহ
    0.34
    POSITIVE LOGITS
    ()
    1.09
    ();
    0.89
    ().
    0.88
    ("
    0.87
    (),
    0.86
    ())
    0.84
    ()]
    0.78
    (
    0.77
    ('
    0.75
    ((
    0.75
    Act Density 0.173%

    No Known Activations