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

    Neuronpedia

    INDEX
    Explanations

    scientific data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dios
    -0.07
     služeb
    -0.06
    Př
    -0.06
     underway
    -0.06
     ngại
    -0.06
     보내
    -0.06
    　　　　
    -0.06
    Submitted
    -0.06
     männer
    -0.06
     nargs
    -0.06
    POSITIVE LOGITS
    _grade
    0.07
     poke
    0.06
    (custom
    0.06
    Living
    0.06
    ーバ
    0.06
    [col
    0.06
    (filter
    0.06
    ↵↵
    0.06
     مب
    0.06
     Flake
    0.06
    Act Density 0.017%

    No Known Activations