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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Render
    -0.08
    possibly
    -0.07
     hepsi
    -0.07
    information
    -0.07
     presentViewController
    -0.07
     مشخص
    -0.07
    private
    -0.07
    */}↵
    -0.07
    spawn
    -0.06
    chrift
    -0.06
    POSITIVE LOGITS
    祖
    0.07
     Maze
    0.06
     Citizenship
    0.06
     které
    0.06
    ρί
    0.05
     DOE
    0.05
     Dương
    0.05
     Aussie
    0.05
    .kr
    0.05
     Mär
    0.05
    Act Density 0.011%

    No Known Activations