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

    Neuronpedia

    INDEX
    Explanations

    sauce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dır
    0.95
    IN
    0.94
    AN
    0.92
     summar
    0.91
    да
    0.88
     surcharge
    0.87
     ginseng
    0.86
     pharmacy
    0.83
     rooster
    0.83
    .
    0.83
    POSITIVE LOGITS
    :
    1.02
    ти
    0.97
    p
    0.94
    pengaruhi
    0.90
    im
    0.82
    ur
    0.81
    </h4>
    0.81
    વે
    0.81
    年轻
    0.80
    一定的
    0.80
    Act Density 0.002%

    No Known Activations