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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     umbrella
    -0.07
     Gould
    -0.07
    .uuid
    -0.07
     pall
    -0.06
    (fetch
    -0.06
     kum
    -0.06
     CHO
    -0.06
     queryString
    -0.06
     ranks
    -0.06
    NSAttributedString
    -0.06
    POSITIVE LOGITS
     Superv
    0.07
    211
    0.07
     Andreas
    0.06
    три
    0.06
    210
    0.06
     Ever
    0.06
    愿
    0.06
     addressed
    0.06
     surprises
    0.06
     Ini
    0.06
    Act Density 0.142%

    No Known Activations