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

    Neuronpedia

    INDEX
    Explanations

    HTML comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    عداد
    -0.06
     HDC
    -0.06
    ۱۳۹
    -0.06
     "("
    -0.06
    む
    -0.06
     ／
    -0.06
    '",
    -0.06
     EQ
    -0.06
    速度
    -0.06
    ]",
    -0.06
    POSITIVE LOGITS
    need
    0.07
     Worksheets
    0.07
    inning
    0.06
     Townsend
    0.06
    Episode
    0.06
    coli
    0.06
     phim
    0.06
     hiç
    0.06
    滑
    0.06
     maze
    0.06
    Act Density 0.001%

    No Known Activations