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

    Neuronpedia

    INDEX
    Explanations

    0 to 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ੫
    1.43
    ты
    1.42
    ლებელია
    1.41
     обеспечи
    1.36
     dast
    1.25
    thats
    1.24
     ensues
    1.23
     ਕੀਤੀ
    1.23
     обеспечивает
    1.22
    дентификаторы
    1.22
    POSITIVE LOGITS
    1.15
    IN
    1.10
    ATION
    1.04
    Airline
    1.01
    대표
    1.01
    AC
    0.98
    ه‌ای
    0.98
    ラ
    0.98
    IS
    0.97
    愔
    0.97
    Act Density 0.534%

    No Known Activations