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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    v
    0.59
    x
    0.58
     -
    0.54
    tt
    0.51
    o
    0.50
    nd
    0.49
     +
    0.47
    name
    0.47
     =
    0.46
    -
    0.46
    POSITIVE LOGITS
    Zawodnik
    0.48
     শ্রমিক
    0.48
    Für
    0.46
     শ্রম
    0.46
    Participants
    0.46
    Người
    0.45
     Gippsland
    0.45
    Sumber
    0.44
    𒉺
    0.44
    鹬
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.