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

    Neuronpedia

    INDEX
    Explanations

    stylesheet links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    மில்லை
    0.39
    ⚭
    0.38
    蛇
    0.38
     câștig
    0.37
     empre
    0.36
     Dynkin
    0.36
    preload
    0.36
    ষ্কার
    0.36
     refor
    0.36
    alık
    0.36
    POSITIVE LOGITS
     فارسی
    0.42
     gratuitement
    0.41
    രാണ്
    0.38
     FIXED
    0.36
     toughest
    0.36
    ء
    0.35
     precipitates
    0.35
    arati
    0.34
    Titanic
    0.34
     administrativas
    0.33
    Act Density 0.001%

    No Known Activations