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

    Neuronpedia

    INDEX
    Explanations

    jury selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     };↵↵↵
    -0.06
     groom
    -0.06
     cow
    -0.06
    _gshared
    -0.06
     regression
    -0.06
    商品
    -0.06
    Night
    -0.06
    bmp
    -0.06
     lobbyist
    -0.06
    .Enums
    -0.06
    POSITIVE LOGITS
    люча
    0.08
    SK
    0.06
    (Photo
    0.06
     kapit
    0.06
     stál
    0.06
     졸
    0.06
     complication
    0.06
    .communication
    0.06
    tha
    0.06
    -sem
    0.06
    Act Density 0.002%

    No Known Activations