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

    Neuronpedia

    INDEX
    Explanations

    context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    餐饮
    -0.08
    跆
    -0.07
    choice
    -0.07
    流
    -0.07
    캘
    -0.07
    条件下
    -0.06
    饥
    -0.06
    �
    -0.06
    Lim
    -0.06
    仅供
    -0.06
    POSITIVE LOGITS
    .Detail
    0.07
    듸
    0.07
     report
    0.07
     "\",
    0.07
    工作
    0.06
    找到了
    0.06
     Cedar
    0.06
    二维码
    0.06
     实
    0.06
     стать
    0.06
    Act Density 0.019%

    No Known Activations