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

    Neuronpedia

    INDEX
    Explanations

    vim configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chrom
    -0.07
     Circ
    -0.06
     (>
    -0.06
    Hillary
    -0.06
     Hillary
    -0.06
     Atlanta
    -0.06
    Improved
    -0.06
     frustrated
    -0.06
     attic
    -0.06
    Lady
    -0.06
    POSITIVE LOGITS
    готов
    0.07
    formik
    0.07
        ↵    ↵    ↵
    0.07
    Nonnull
    0.07
     čty
    0.07
    jekt
    0.07
     kutje
    0.06
     předsed
    0.06
    PMC
    0.06
     xlabel
    0.06
    Act Density 0.010%

    No Known Activations