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

    Neuronpedia

    INDEX
    Explanations

    package

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Atkins
    -0.08
     widgets
    -0.08
     bottoms
    -0.07
     fitted
    -0.06
    .grid
    -0.06
     지정
    -0.06
     zůst
    -0.06
     tặng
    -0.06
     tst
    -0.06
     crist
    -0.06
    POSITIVE LOGITS
    .ActionListener
    0.07
     nào
    0.06
    Overlap
    0.06
    programs
    0.06
     giveaway
    0.06
    使用
    0.06
    協
    0.06
    _lit
    0.06
     зни
    0.06
    _HEADERS
    0.06
    Act Density 0.002%

    No Known Activations