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

    Neuronpedia

    INDEX
    Explanations

    classic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adjust
    -0.07
    ộn
    -0.06
    ゆ
    -0.06
     Initial
    -0.06
     national
    -0.06
    _fatal
    -0.06
    .Errors
    -0.06
     dragged
    -0.06
     giám
    -0.06
    December
    -0.06
    POSITIVE LOGITS
     classic
    0.09
    Classic
    0.07
    classic
    0.07
     Classic
    0.06
    LOYEE
    0.06
     bye
    0.06
    ौज
    0.06
    (rad
    0.06
    羊
    0.06
    _usr
    0.06
    Act Density 0.052%

    No Known Activations