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

    Neuronpedia

    INDEX
    Explanations

    y and y-like characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    1.24
    s
    1.09
    a
    1.09
    িন
    1.06
     vasodil
    0.99
    ن
    0.97
    ীয়
    0.95
    prefetch
    0.93
    sour
    0.93
    ة
    0.92
    POSITIVE LOGITS
    yyyyyyyy
    1.62
    yyyy
    1.30
    ுள்ளனர்
    1.25
    ுள்ளார்
    1.24
    и
    1.18
     compris
    1.17
    yy
    1.05
    о
    1.02
    ਰ
    0.98
    tta
    0.96
    Act Density 0.256%

    No Known Activations