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

    Neuronpedia

    INDEX
    Explanations

    royalty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     předpis
    -0.07
     shopper
    -0.07
     articulated
    -0.07
    GN
    -0.07
     callers
    -0.07
     cerv
    -0.06
     Kür
    -0.06
     cages
    -0.06
    ์เซ
    -0.06
     thiệu
    -0.06
    POSITIVE LOGITS
     king
    0.07
     entails
    0.06
     airports
    0.06
    801
    0.06
     UserName
    0.06
    Cheap
    0.06
    isOk
    0.06
     理
    0.06
    좋
    0.06
    aar
    0.05
    Act Density 0.013%

    No Known Activations