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

    Neuronpedia

    INDEX
    Explanations

    given

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Range
    -0.07
     unw
    -0.07
    леж
    -0.07
    ителей
    -0.07
     cabin
    -0.06
    GENERAL
    -0.06
    “At
    -0.06
    "At
    -0.06
     grains
    -0.06
    AntiForgeryToken
    -0.06
    POSITIVE LOGITS
    ="+
    0.07
     Pty
    0.06
     asked
    0.06
    ......
    0.06
    题
    0.06
    喔
    0.06
    ?";↵
    0.06
    Slinky
    0.06
     ще
    0.06
     spilled
    0.06
    Act Density 0.033%

    No Known Activations