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

    Neuronpedia

    INDEX
    Explanations

    Defining normal behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Subject
    -0.07
     $_
    -0.07
     giác
    -0.07
    _FEED
    -0.07
    ỉ
    -0.06
    目に
    -0.06
     *((
    -0.06
    你需要
    -0.06
    .RGB
    -0.06
    .href
    -0.06
    POSITIVE LOGITS
    Danny
    0.08
    给别人
    0.07
    WebService
    0.07
    :v
    0.07
    _widget
    0.07
    糟糕
    0.06
     لبنان
    0.06
    .aws
    0.06
    .internal
    0.06
    ✿
    0.06
    Act Density 0.090%

    No Known Activations