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

    Neuronpedia

    INDEX
    Explanations

    publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DataSet
    -0.07
    上去
    -0.07
    给大家
    -0.07
     setType
    -0.07
    .sessions
    -0.07
    Ѱ
    -0.07
    _RADIO
    -0.07
     Investing
    -0.07
    意識
    -0.07
    )#
    -0.07
    POSITIVE LOGITS
    rotation
    0.08
     Mariners
    0.08
    grades
    0.07
    legs
    0.07
     container
    0.07
    ogh
    0.07
    Badge
    0.07
    Templates
    0.07
     yapıl
    0.07
     binary
    0.07
    Act Density 0.007%

    No Known Activations