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
     merits
    -0.07
    logan
    -0.06
    lland
    -0.06
    funcs
    -0.06
    ovní
    -0.06
    βε
    -0.06
     एप
    -0.06
    marvin
    -0.06
     count
    -0.06
    (Syntax
    -0.06
    POSITIVE LOGITS
     Weather
    0.07
    ایش
    0.07
     Anglic
    0.07
    ])↵↵
    0.07
    /pro
    0.07
    weather
    0.07
                       ↵
    0.06
       ↵    ↵
    0.06
    ))))↵
    0.06
    ".↵↵↵↵
    0.06
    Act Density 0.067%

    No Known Activations