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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sunn
    -0.10
     livestream
    -0.09
     dais
    -0.09
     Artist
    -0.08
     receita
    -0.08
     Kamu
    -0.08
     Sandwich
    -0.08
     концерт
    -0.08
     Summer
    -0.08
     butter
    -0.08
    POSITIVE LOGITS
    ensional
    0.08
     unrestricted
    0.08
    扩
    0.08
     além
    0.08
     associative
    0.08
    XPath
    0.08
    uent
    0.07
    :auto
    0.07
    语言
    0.07
     cylindrical
    0.07
    Act Density 0.003%

    No Known Activations