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

    Neuronpedia

    INDEX
    Explanations

    Point, points, and what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    1.74
    ні
    1.48
    ру
    1.25
    ных
    1.18
    ري
    1.18
    ς
    1.16
    v
    1.13
    ك
    1.13
    ро
    1.11
    то
    1.11
    POSITIVE LOGITS
    n
    1.38
    ⦖
    1.09
    ak
    1.06
    >
    1.05
    ন
    1.05
    밂
    1.05
    न
    1.03
    nä
    0.99
    ique
    0.98
    น
    0.94
    Act Density 0.067%

    No Known Activations