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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    上午
    1.48
     وش
    1.30
    收藏
    1.24
    早上
    1.23
    ों
    1.18
     শিক্ষা
    1.17
    ের
    1.17
     器
    1.16
    aan
    1.15
    ್
    1.12
    POSITIVE LOGITS
     limitaciones
    1.06
     Disse
    1.04
     dibandingkan
    1.02
    ško
    0.98
    tting
    0.96
     dernier
    0.93
     predict
    0.93
     délai
    0.91
     milder
    0.91
     explicado
    0.89
    Act Density 0.003%

    No Known Activations