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

    Neuronpedia

    INDEX
    Explanations

    Physical exercises/movements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ẠI
    -0.07
    陵
    -0.07
    特色产业
    -0.07
    確實
    -0.07
    ain
    -0.07
     misery
    -0.06
    itra
    -0.06
    .As
    -0.06
    不排除
    -0.06
    中国传统
    -0.06
    POSITIVE LOGITS
     Bench
    0.08
     באות
    0.07
     removes
    0.07
    (report
    0.07
    (argc
    0.07
     pontos
    0.07
    agency
    0.07
    สอง
    0.07
     berth
    0.07
     пс
    0.07
    Act Density 0.027%

    No Known Activations