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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    个国家
    -0.08
     japon
    -0.07
    小說
    -0.07
    cliffe
    -0.07
    >F
    -0.07
    ℰ
    -0.07
     Selenium
    -0.07
    ศา
    -0.07
    劑
    -0.07
    넑
    -0.07
    POSITIVE LOGITS
    .Bytes
    0.07
    Row
    0.07
    _else
    0.07
    _suffix
    0.07
     employ
    0.07
     Scot
    0.07
    حز
    0.06
    angled
    0.06
     Outputs
    0.06
     Root
    0.06
    Act Density 0.063%

    No Known Activations