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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )").
    -0.07
     пок
    -0.07
    apas
    -0.07
    /import
    -0.07
    也不敢
    -0.07
    _texts
    -0.06
     oa
    -0.06
    ᯙ
    -0.06
     cached
    -0.06
     wz
    -0.06
    POSITIVE LOGITS
    瓷器
    0.07
    ERENCE
    0.07
    制冷
    0.07
    甜蜜
    0.07
    mons
    0.07
    菜品
    0.07
    道德
    0.07
    词汇
    0.06
    otyp
    0.06
     vực
    0.06
    Act Density 0.071%

    No Known Activations