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

    Neuronpedia

    INDEX
    Explanations

    scientific measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    杯
    -0.06
     prisoner
    -0.06
    -м
    -0.06
    .RIGHT
    -0.06
    705
    -0.06
    Simple
    -0.06
    _while
    -0.06
     Transform
    -0.06
    060
    -0.06
    POSITIVE LOGITS
    ностей
    0.08
     noi
    0.06
    Clicked
    0.06
     Soup
    0.06
     setValue
    0.06
    (required
    0.06
     徒
    0.06
     Thổ
    0.06
     并
    0.06
    оратив
    0.06
    Act Density 0.113%

    No Known Activations