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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     武
    -0.07
     Tân
    -0.07
     silah
    -0.07
    有限
    -0.07
    _services
    -0.06
    ۱۹۴
    -0.06
    ่ย
    -0.06
    avelength
    -0.06
     iCloud
    -0.06
    785
    -0.06
    POSITIVE LOGITS
    namese
    0.07
    ایل
    0.06
     SO
    0.06
    {\
    0.06
    /****************************************************************
    0.06
     consumption
    0.06
    ughty
    0.06
     fragmentation
    0.06
    thritis
    0.06
     flipping
    0.06
    Act Density 0.027%

    No Known Activations