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

    Neuronpedia

    INDEX
    Explanations

    twitter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .PI
    -0.07
     사진
    -0.07
    (nav
    -0.06
    MISSION
    -0.06
    піон
    -0.06
    /Home
    -0.06
    _pi
    -0.06
    肖
    -0.06
     Loose
    -0.06
    وپ
    -0.06
    POSITIVE LOGITS
    dik
    0.06
    sage
    0.06
    ponential
    0.06
    emark
    0.06
     unanimous
    0.06
     spared
    0.06
    daq
    0.06
     exponential
    0.06
     navy
    0.05
    ây
    0.05
    Act Density 0.014%

    No Known Activations