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

    Neuronpedia

    INDEX
    Explanations

    .models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    降低
    -0.07
    的感受
    -0.07
    _python
    -0.07
    ндекс
    -0.07
     variety
    -0.07
     perennial
    -0.07
     Ginger
    -0.07
     Укра
    -0.07
     flu
    -0.07
    istrib
    -0.07
    POSITIVE LOGITS
    District
    0.07
    ActivityIndicatorView
    0.07
    ']}'
    0.06
    玘
    0.06
    ;">
↵
    0.06
    出轨
    0.06
    バレ
    0.06
    .Charting
    0.06
    瑬
    0.06
    햏
    0.06
    Act Density 0.001%

    No Known Activations