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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    豸
    -0.07
    系列活动
    -0.07
    mallow
    -0.06
    㰀
    -0.06
    “Our
    -0.06
    投票
    -0.06
    个城市
    -0.06
     },{↵
    -0.06
    曝
    -0.06
    .reference
    -0.06
    POSITIVE LOGITS
    .prob
    0.07
    精确
    0.07
    0.07
     Gre
    0.07
    触摸
    0.07
    0.07
    eligible
    0.07
    加倍
    0.07
    ession
    0.07
     planes
    0.07
    Act Density 0.124%

    No Known Activations