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

    Neuronpedia

    INDEX
    Explanations

    check websites and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x0D>
    1.16
    </h2>
    1.02
    </u>
    0.97
    </h5>
    0.94
    </h4>
    0.91
    ‬
    0.89
    </em>
    0.88
    </strong>
    0.86
    ]，
    0.84
    。\
    0.80
    POSITIVE LOGITS
    ด
    1.04
    is
    0.94
    م
    0.89
    ع
    0.86
    ৬
    0.86
    ות
    0.83
    ב
    0.82
    ü
    0.82
     journeys
    0.80
    em
    0.80
    Act Density 0.027%

    No Known Activations