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

    Neuronpedia

    INDEX
    Explanations

    piece

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attitude
    -0.07
    Nat
    -0.07
     onay
    -0.07
    -таки
    -0.06
    valuation
    -0.06
    thern
    -0.06
     Barrett
    -0.06
     Lyon
    -0.06
    	al
    -0.06
    _fun
    -0.06
    POSITIVE LOGITS
     piece
    0.18
     pieces
    0.17
    piece
    0.14
     Pieces
    0.14
     Piece
    0.13
    Piece
    0.12
    pieces
    0.11
    -piece
    0.10
    (piece
    0.10
     PIE
    0.10
    Act Density 0.018%

    No Known Activations