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

    Neuronpedia

    INDEX
    Explanations

    DW

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crank
    -0.08
     verr
    -0.07
     onFailure
    -0.07
    产业结构
    -0.07
    Vers
    -0.07
     Iss
    -0.07
     ros
    -0.07
     Ard
    -0.07
     ער
    -0.06
    查看详情
    -0.06
    POSITIVE LOGITS
    地震
    0.07
    ኦ
    0.07
     Tigers
    0.07
     detailing
    0.07
    玟
    0.07
    꿩
    0.06
    /videos
    0.06
    绘制
    0.06
    client
    0.06
     _
↵
    0.06
    Act Density 0.003%

    No Known Activations