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

    Neuronpedia

    INDEX
    Explanations

    newborn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qu
    -0.08
    edio
    -0.08
     course
    -0.07
    Hover
    -0.07
    _USAGE
    -0.07
    ans
    -0.07
    上级
    -0.07
    (version
    -0.07
    不上
    -0.07
     userDetails
    -0.07
    POSITIVE LOGITS
    )--
    0.08
    تنظيم
    0.08
     Horm
    0.07
    굠
    0.07
     practices
    0.07
    Latch
    0.07
     Elect
    0.07
    族自治
    0.07
    agged
    0.07
     styling
    0.07
    Act Density 0.004%

    No Known Activations