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

    Neuronpedia

    INDEX
    Explanations

    code, mazes, grids

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    페이지
    -0.06
    TeV
    -0.06
    дами
    -0.06
     služ
    -0.06
     муль
    -0.06
    Req
    -0.06
    男人
    -0.06
     unlikely
    -0.06
    医
    -0.06
    (World
    -0.06
    POSITIVE LOGITS
     UserProfile
    0.07
     presenting
    0.07
    /gen
    0.07
     ομάδα
    0.07
     JWT
    0.06
     archive
    0.06
     rate
    0.06
     GetLastError
    0.06
     brat
    0.06
    _interp
    0.06
    Act Density 0.015%

    No Known Activations