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

    Neuronpedia

    INDEX
    Explanations

    married

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    implicitly
    -0.08
    ▼
    -0.07
    新闻中心
    -0.07
    🏥
    -0.07
    -oper
    -0.07
    コミュニケ
    -0.06
    向记者
    -0.06
    Ն
    -0.06
     hotter
    -0.06
    🔻
    -0.06
    POSITIVE LOGITS
    ystals
    0.10
     Normal
    0.07
    _IList
    0.07
    جال
    0.07
    月亮
    0.07
    PasswordField
    0.07
    常
    0.07
     affects
    0.06
    SY
    0.06
    好
    0.06
    Act Density 0.014%

    No Known Activations