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

    Neuronpedia

    INDEX
    Explanations

    Businesses and services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .prototype
    -0.08
     textStyle
    -0.07
     incentives
    -0.07
    -made
    -0.06
    作用
    -0.06
    enting
    -0.06
     nursing
    -0.06
     instead
    -0.06
     eat
    -0.06
     Auction
    -0.06
    POSITIVE LOGITS
    abble
    0.07
    จำก
    0.07
    เปล
    0.06
     ranked
    0.06
    ากล
    0.06
     aggreg
    0.06
    ELSE
    0.06
    ами
    0.06
    верж
    0.06
     Перед
    0.06
    Act Density 0.160%

    No Known Activations