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

    Neuronpedia

    INDEX
    Explanations

    Code/URLs/File paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jets
    -0.07
    Pawn
    -0.07
     fake
    -0.07
    .requests
    -0.07
     dumb
    -0.07
    .driver
    -0.07
    /pass
    -0.06
     median
    -0.06
    Missing
    -0.06
    _ring
    -0.06
    POSITIVE LOGITS
    ill
    0.06
     Gonz
    0.06
     "'",
    0.06
     UNESCO
    0.06
    ills
    0.06
    fl
    0.06
     }>↵
    0.06
    '>".$
    0.06
    (platform
    0.06
     /*!
    0.06
    Act Density 0.008%

    No Known Activations