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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     is
    -0.91
    is
    -0.57
     удовольствием
    -0.46
    是
    -0.45
     đó
    -0.42
     blijft
    -0.42
     gehört
    -0.41
    Ze
    -0.41
    which
    -0.41
     coloris
    -0.41
    POSITIVE LOGITS
     initComponents
    0.95
    SharedDtor
    0.92
     StatefulWidget
    0.91
    IntoConstraints
    0.88
    ]--;
    0.80
     صوتيه
    0.79
     EconPapers
    0.78
     indestru
    0.77
     للاسماء
    0.77
    MergeFrom
    0.77
    Act Density 0.123%

    No Known Activations