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

    Neuronpedia

    INDEX
    Explanations

    HTML table formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fx
    -0.07
    _lot
    -0.07
     Kami
    -0.06
     '}↵
    -0.06
     masks
    -0.06
     bonds
    -0.06
     "}↵
    -0.06
    .fun
    -0.06
     spy
    -0.06
    500
    -0.06
    POSITIVE LOGITS
    ゲーム
    0.06
     Guess
    0.06
    ates
    0.06
    пор
    0.06
     політики
    0.06
     Gian
    0.06
    ορ
    0.06
    ы
    0.06
     turnaround
    0.06
    unas
    0.06
    Act Density 0.036%

    No Known Activations