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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Canon
    -0.06
     advertisements
    -0.06
     ST
    -0.06
     Carter
    -0.06
    ژن
    -0.06
     printer
    -0.06
    ство
    -0.06
     :
    -0.06
     더
    -0.06
    ік
    -0.06
    POSITIVE LOGITS
     tento
    0.07
     [↵↵
    0.06
    kün
    0.06
     Spreadsheet
    0.06
    filtr
    0.06
     muscular
    0.06
    ramework
    0.06
    :nil
    0.06
    ủy
    0.06
     Smithsonian
    0.06
    Act Density 0.003%

    No Known Activations