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

    Neuronpedia

    INDEX
    Explanations

    MP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pong
    -0.07
     slashing
    -0.07
    lack
    -0.07
    服務
    -0.06
    _SUCCESS
    -0.06
     Mines
    -0.06
     stare
    -0.06
    usra
    -0.06
     USER
    -0.06
    дем
    -0.06
    POSITIVE LOGITS
     그의
    0.06
    ignant
    0.06
    ensive
    0.06
    食べ
    0.06
    ьми
    0.06
    歳
    0.06
    }
    0.06
    PA
    0.06
     وهو
    0.06
     surviving
    0.06
    Act Density 0.059%

    No Known Activations