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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,'
    -0.07
    busy
    -0.07
     decades
    -0.07
    .rect
    -0.07
    市
    -0.07
    رد
    -0.06
    우스
    -0.06
    عي
    -0.06
    SAN
    -0.06
    Va
    -0.06
    POSITIVE LOGITS
    微软雅黑
    0.07
     zoek
    0.06
     toJSON
    0.06
    】↵
    0.06
    moduleName
    0.06
    -step
    0.06
    .Filters
    0.06
    های
    0.06
    .Split
    0.05
    zyć
    0.05
    Act Density 0.035%

    No Known Activations