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

    Neuronpedia

    INDEX
    Explanations

    Win

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    look
    -0.07
    struct
    -0.07
     dataIndex
    -0.07
    도로
    -0.06
    .interface
    -0.06
    álie
    -0.06
     Hình
    -0.06
     груд
    -0.06
     ارتف
    -0.06
     IICIII
    -0.06
    POSITIVE LOGITS
     win
    0.13
     Win
    0.11
     winners
    0.11
     winning
    0.11
     won
    0.11
    win
    0.10
     wins
    0.10
     Winners
    0.10
    Win
    0.09
    Winner
    0.09
    Act Density 0.031%

    No Known Activations