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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    です
    -0.08
    TimeZone
    -0.07
    Про
    -0.07
    poi
    -0.07
    staw
    -0.06
    Est
    -0.06
    Pow
    -0.06
    _Enter
    -0.06
    دم
    -0.06
    iva
    -0.06
    POSITIVE LOGITS
     gzip
    0.07
    .Column
    0.07
    <Product
    0.07
     bits
    0.07
     asserts
    0.06
    Implement
    0.06
     Player
    0.06
    )↵↵↵↵↵
    0.06
    ť
    0.06
    .／
    0.06
    Act Density 0.024%

    No Known Activations