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

    Neuronpedia

    INDEX
    Explanations

    computational efficiency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sterdam
    -0.07
    ders
    -0.06
    convert
    -0.06
    abant
    -0.06
     towns
    -0.06
    ge
    -0.06
     ripped
    -0.06
    .ru
    -0.06
    いう
    -0.06
    ยก
    -0.06
    POSITIVE LOGITS
     Behavioral
    0.07
    면적
    0.07
    _Global
    0.06
     WebDriver
    0.06
     server
    0.06
    _Static
    0.06
    _fs
    0.06
    [right
    0.06
    (path
    0.06
    aravel
    0.06
    Act Density 0.062%

    No Known Activations