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

    Neuronpedia

    INDEX
    Explanations

    rotating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дня
    -0.07
    errer
    -0.07
    iamo
    -0.07
    \Config
    -0.06
     @_;↵
    -0.06
     decir
    -0.06
    ’.
    -0.06
    atta
    -0.06
    errat
    -0.06
     Terraria
    -0.06
    POSITIVE LOGITS
     HomePage
    0.06
     caring
    0.06
     opts
    0.06
     Olympics
    0.06
     Running
    0.06
    _page
    0.06
    最後
    0.06
    thanks
    0.06
    cells
    0.06
     runway
    0.05
    Act Density 0.008%

    No Known Activations