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

    Neuronpedia

    INDEX
    Explanations

    deal or deals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    1.30
    ции
    1.05
    но
    1.03
    ни
    1.00
    с
    0.95
    </h1>
    0.95
    </h2>
    0.95
    ى
    0.95
    </sup>
    0.92
    </h3>
    0.91
    POSITIVE LOGITS
    টি
    1.32
    (
    1.23
    ’
    1.15
    ﺍ
    1.06
    al
    1.02
     Deals
    1.00
    Від
    0.97
    िंग
    0.96
     deals
    0.94
    '
    0.94
    Act Density 0.006%

    No Known Activations