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

    Neuronpedia

    INDEX
    Explanations

    Police

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DAM
    -0.07
     undertaken
    -0.07
     马
    -0.06
    /";↵↵
    -0.06
    Dam
    -0.06
    setVisible
    -0.06
    cription
    -0.06
     subtitle
    -0.06
    ,ID
    -0.06
    ceb
    -0.06
    POSITIVE LOGITS
     Veter
    0.07
    _Parse
    0.07
     шкі
    0.06
    /lists
    0.06
     кіль
    0.06
    科技有限公司
    0.06
    _ATTACH
    0.06
    vatel
    0.06
     conflicting
    0.06
    KeyValuePair
    0.06
    Act Density 0.210%

    No Known Activations