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

    Neuronpedia

    INDEX
    Explanations

    Hopkins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hopkins
    -0.52
     Stage
    -0.48
     Southern
    -0.46
    Southern
    -0.45
    Hopkins
    -0.45
     heavy
    -0.43
    ITÀ
    -0.42
     large
    -0.42
    kwür
    -0.42
    keda
    -0.42
    POSITIVE LOGITS
     RoutedEventArgs
    0.90
    ContextHolder
    0.90
    HandlerContext
    0.86
    UpInside
    0.79
     الحره
    0.76
    Personendaten
    0.76
    Datuak
    0.75
     larmes
    0.75
     supérieurs
    0.75
    UrlResolution
    0.75
    Act Density 0.326%

    No Known Activations