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

    Neuronpedia

    INDEX
    Explanations

    sample

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dır
    -0.08
    Rail
    -0.08
    Glass
    -0.08
    langs
    -0.08
     нас
    -0.07
     Languages
    -0.07
     trợ
    -0.07
    cock
    -0.07
     Comisión
    -0.07
     réussir
    -0.07
    POSITIVE LOGITS
     데이터를
    0.12
    数据
    0.11
     observations
    0.11
     데이터
    0.10
     muestras
    0.10
     بيانات
    0.10
     gegevens
    0.10
     data
    0.10
     snapshot
    0.09
     iid
    0.09
    Act Density 0.011%

    No Known Activations