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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iw
    -0.06
    ('?
    -0.06
    ienen
    -0.06
    扬
    -0.06
     Maze
    -0.06
    .same
    -0.06
    _VAL
    -0.06
    漫
    -0.06
     Spend
    -0.06
    ien
    -0.06
    POSITIVE LOGITS
     consectetur
    0.07
     Dummy
    0.06
     ولم
    0.06
     quick
    0.06
    regon
    0.06
    促
    0.06
     particip
    0.06
    	first
    0.06
     presumably
    0.06
    пис
    0.06
    Act Density 0.016%

    No Known Activations