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

    Neuronpedia

    INDEX
    Explanations

    growth and charts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     determinate
    0.64
     our
    0.64
     ठिका
    0.62
    賤
    0.62
     definite
    0.62
    定
    0.62
     Bright
    0.60
    umann
    0.60
    难
    0.60
     need
    0.59
    POSITIVE LOGITS
     gráfico
    1.03
     chart
    1.02
    Chart
    0.98
     CHART
    0.95
     Grafik
    0.94
     Chart
    0.94
     gráfica
    0.92
    chart
    0.91
    Growth
    0.90
    écran
    0.90
    Act Density 0.000%

    No Known Activations