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

    Neuronpedia

    INDEX
    Explanations

    hyphens and slashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쭙
    -0.07
    ograms
    -0.07
     agréable
    -0.07
     aslı
    -0.07
    .requests
    -0.07
     rootView
    -0.07
    它
    -0.06
     professionnel
    -0.06
    知道自己
    -0.06
    انب
    -0.06
    POSITIVE LOGITS
    .Stage
    0.07
     pits
    0.07
    -selected
    0.07
    .Paint
    0.07
    кат
    0.06
    所需的
    0.06
    嵯
    0.06
    inka
    0.06
     jan
    0.06
     Nik
    0.06
    Act Density 0.027%

    No Known Activations