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

    Neuronpedia

    INDEX
    Explanations

    poster

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рай
    -0.08
    .Platform
    -0.08
     Waterloo
    -0.07
    필
    -0.07
    跑道
    -0.07
    仅供
    -0.07
    サイ
    -0.07
     allocated
    -0.07
    رأس
    -0.07
     الان
    -0.07
    POSITIVE LOGITS
    𐤂
    0.09
    ߖ
    0.08
     swingerclub
    0.07
    twor
    0.07
     FIG
    0.07
    obe
    0.07
     qa
    0.07
     XCTestCase
    0.07
    .prototype
    0.07
    稚
    0.06
    Act Density 0.002%

    No Known Activations