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

    Neuronpedia

    INDEX
    Explanations

    computer code/files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     converts
    -0.07
    inin
    -0.07
     centrally
    -0.06
     timetable
    -0.06
     isAdmin
    -0.06
    оны
    -0.06
     Survey
    -0.06
     тов
    -0.06
     snippets
    -0.06
     survey
    -0.06
    POSITIVE LOGITS
     ballet
    0.07
    underscore
    0.07
    (currency
    0.07
    ूज
    0.07
     averaging
    0.07
    送
    0.07
    ?!
    0.07
     retr
    0.06
    getX
    0.06
     взя
    0.06
    Act Density 0.001%

    No Known Activations