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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TUN
    -0.06
    polit
    -0.06
    )\↵
    -0.06
     teb
    -0.06
    _stamp
    -0.06
     recipient
    -0.06
     regarding
    -0.06
    uropean
    -0.06
    lose
    -0.06
     uncon
    -0.06
    POSITIVE LOGITS
    :CGPoint
    0.07
    @stop
    0.07
     Beast
    0.07
    PH
    0.06
    |i
    0.06
    .MAIN
    0.06
    中学
    0.06
     strokeLine
    0.06
    Qual
    0.06
    .Click
    0.06
    Act Density 0.000%

    No Known Activations