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

    Neuronpedia

    INDEX
    Explanations

    simple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ervatives
    -0.07
    middlewares
    -0.07
     normals
    -0.06
    setUp
    -0.06
    涉
    -0.06
    nodiscard
    -0.06
    _brightness
    -0.06
    Xi
    -0.06
    Qual
    -0.06
     topl
    -0.06
    POSITIVE LOGITS
     simple
    0.07
    ượt
    0.07
     컴
    0.07
    OSH
    0.06
    objectManager
    0.06
    ök
    0.06
     Simpsons
    0.06
    :params
    0.06
    Represent
    0.06
     tối
    0.06
    Act Density 0.049%

    No Known Activations