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

    Neuronpedia

    INDEX
    Explanations

    data sources and text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soluzioni
    0.67
    魅力
    0.61
    guess
    0.61
    Functions
    0.61
     Funktionen
    0.60
    Solutions
    0.59
    灵活
    0.59
     tileSize
    0.59
    optimizers
    0.58
    Guess
    0.58
    POSITIVE LOGITS
     documents
    1.96
     data
    1.96
     texts
    1.88
     데이터를
    1.71
     text
    1.62
     datasets
    1.61
    データを
    1.58
    data
    1.57
     documentation
    1.55
     records
    1.52
    Act Density 2.960%

    No Known Activations