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

    Neuronpedia

    INDEX
    Explanations

    Fix problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Middleware
    -0.07
    愍
    -0.07
     århus
    -0.07
     mấy
    -0.06
     محافظة
    -0.06
     baise
    -0.06
    Old
    -0.06
    重组
    -0.06
    𝄅
    -0.06
    Hong
    -0.06
    POSITIVE LOGITS
     Rebel
    0.08
    氮
    0.08
    don
    0.08
    uib
    0.07
    客户的
    0.07
    .Bl
    0.07
    ヘル
    0.07
    客户
    0.07
    为抓
    0.07
    нер
    0.07
    Act Density 0.040%

    No Known Activations