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

    Neuronpedia

    INDEX
    Explanations

    uniform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kání
    -0.06
     Delta
    -0.06
     інтерес
    -0.06
    _OVERRIDE
    -0.06
     alice
    -0.06
    [next
    -0.06
     otra
    -0.06
    @app
    -0.06
    essages
    -0.06
    (est
    -0.06
    POSITIVE LOGITS
     uniform
    0.12
     Uniform
    0.09
     uniformly
    0.08
    Uniform
    0.08
    .Style
    0.07
     Un
    0.07
    uniform
    0.07
     Baum
    0.07
     unpack
    0.07
     AND
    0.07
    Act Density 0.008%

    No Known Activations