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

    Neuronpedia

    INDEX
    Explanations

    increasingly complex world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     normally
    0.42
     auraient
    0.41
     would
    0.41
    Normally
    0.40
     usually
    0.40
     podría
    0.38
    athyroid
    0.38
    Would
    0.38
     pthread
    0.38
     slightly
    0.38
    POSITIVE LOGITS
     Increasingly
    1.02
     increasingly
    1.02
     globalization
    1.00
    越來越
    0.96
     globalisation
    0.96
    越来越
    0.95
     digitalization
    0.95
    Globalization
    0.91
    越来越多
    0.91
     технологий
    0.88
    Act Density 0.067%

    No Known Activations