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

    Neuronpedia

    INDEX
    Explanations

    USMLE exam questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    1.17
    자
    0.96
    ()
    0.94
    ير
    0.91
    ﻜ
    0.90
    트
    0.89
     erinnert
    0.88
    '";
    0.87
     komen
    0.84
     zeigte
    0.83
    POSITIVE LOGITS
     to
    1.44
     by
    1.13
    ت
    1.08
    as
    1.06
     (
    1.06
    िग
    1.06
    ین
    1.03
    inat
    1.01
    ل
    0.99
    by
    0.97
    Act Density 0.000%

    No Known Activations