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

    Neuronpedia

    INDEX
    Explanations

    code and technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Drawing
    -0.07
    warning
    -0.07
    PEnd
    -0.06
    _station
    -0.06
     cùng
    -0.06
    panic
    -0.06
    ัญญ
    -0.06
    .then
    -0.06
    수의
    -0.06
    Throws
    -0.06
    POSITIVE LOGITS
     большой
    0.07
    生成
    0.06
     FRAME
    0.06
     elders
    0.06
     Mel
    0.06
    .imageView
    0.06
     století
    0.06
    рол
    0.06
     Attend
    0.06
     uvád
    0.06
    Act Density 0.000%

    No Known Activations