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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oders
    -0.09
    (force
    -0.08
    tır
    -0.07
     تص
    -0.07
    :get
    -0.07
    yaml
    -0.07
     Forward
    -0.07
    明白了
    -0.07
     المزيد
    -0.07
     зад
    -0.07
    POSITIVE LOGITS
    סקס
    0.08
     ego
    0.07
    .barDockControl
    0.07
    星级酒店
    0.07
    احتجاج
    0.07
    🌉
    0.07
    ＠
    0.06
    �
    0.06
    技术服务
    0.06
    ㈰
    0.06
    Act Density 0.003%

    No Known Activations