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

    Neuronpedia

    INDEX
    Explanations

    matrices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xlabel
    -0.07
     위치
    -0.07
     Oro
    -0.07
     upwards
    -0.07
     Voc
    -0.06
    丈夫
    -0.06
    otes
    -0.06
    _alg
    -0.06
    ouis
    -0.06
     INSERT
    -0.06
    POSITIVE LOGITS
     enforcement
    0.07
     decking
    0.06
    essor
    0.06
    _screen
    0.06
    antics
    0.06
     successor
    0.06
    utherford
    0.06
    =title
    0.06
    gregated
    0.06
     restriction
    0.06
    Act Density 0.002%

    No Known Activations