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

    Neuronpedia

    INDEX
    Explanations

    contractions with not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     busty
    -0.07
    (original
    -0.07
     Ну
    -0.06
     MJ
    -0.06
     UserRole
    -0.06
     Her
    -0.06
     Comput
    -0.06
    _amt
    -0.06
    _px
    -0.06
     UserManager
    -0.06
    POSITIVE LOGITS
    士
    0.07
     projekt
    0.07
     adjustable
    0.06
     тест
    0.06
    股票
    0.06
     Signal
    0.06
     Algorithm
    0.06
    loomberg
    0.06
    .NOT
    0.06
    .React
    0.06
    Act Density 0.018%

    No Known Activations