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

    Neuronpedia

    INDEX
    Explanations

    sports competitions and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘿
    1.16
    mv
    1.00
    cations
    0.96
    所谓的
    0.96
    褥
    0.95
    ులు
    0.91
    GRAD
    0.91
    𝙄
    0.91
    𝙃
    0.91
    铺
    0.90
    POSITIVE LOGITS
    ar
    1.30
    ار
    1.12
     existent
    1.01
     prilikom
    1.00
    o
    1.00
    ל
    1.00
    ようになりました
    0.98
    ו
    0.98
    ارس
    0.97
    الان
    0.96
    Act Density 0.001%

    No Known Activations