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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    creasing
    -0.07
    ﹢
    -0.07
    젰
    -0.06
    ↶
    -0.06
    EXPORT
    -0.06
    ϰ
    -0.06
    .Mock
    -0.06
    房地产
    -0.06
    丫
    -0.06
    路径
    -0.06
    POSITIVE LOGITS
     offensive
    0.08
     muit
    0.07
    信心
    0.07
    (pdev
    0.06
     sucesso
    0.06
     CARD
    0.06
     hız
    0.06
     Deleted
    0.06
     федер
    0.06
     neh
    0.06
    Act Density 0.034%

    No Known Activations