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

    Neuronpedia

    INDEX
    Explanations

    is, be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Increases
    -0.07
    ابي
    -0.06
    _FINISH
    -0.06
     люди
    -0.06
    (codec
    -0.06
    -positive
    -0.06
    attached
    -0.06
    .tableView
    -0.06
    映画
    -0.06
    puts
    -0.06
    POSITIVE LOGITS
    _less
    0.07
    ISP
    0.07
     ší
    0.07
    한다
    0.06
    bw
    0.06
     Cord
    0.06
     yan
    0.06
    gamber
    0.06
     Freud
    0.06
    涉
    0.06
    Act Density 0.072%

    No Known Activations