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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -proxy
    -0.07
    (fake
    -0.07
    ddit
    -0.07
     gấp
    -0.07
    任何一个
    -0.07
    /watch
    -0.06
    提炼
    -0.06
    情境
    -0.06
     rối
    -0.06
    想像
    -0.06
    POSITIVE LOGITS
    软雅黑
    0.07
    _ACT
    0.06
    关
    0.06
     Coun
    0.06
    _responses
    0.06
    ()};↵
    0.06
     Casual
    0.06
     CEO
    0.06
    Ups
    0.06
    .Cloud
    0.06
    Act Density 0.000%

    No Known Activations