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

    Neuronpedia

    INDEX
    Explanations

    discretion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    2.02
    ip
    2.00
    িতে
    1.95
    o
    1.80
    нга
    1.66
    ׁ
    1.66
    oil
    1.52
    utilities
    1.52
    ו
    1.49
    ఖ్య
    1.45
    POSITIVE LOGITS
     óptica
    1.45
    >";
    1.38
    ー
    1.37
     tepat
    1.35
    лор
    1.34
     Sedangkan
    1.34
    ーー
    1.33
     Infin
    1.32
    >[
    1.30
    দিন
    1.29
    Act Density 0.003%

    No Known Activations