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

    Neuronpedia

    INDEX
    Explanations

    protection and regulations (geographic/national)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uptick
    0.66
     عشان
    0.63
     هيكون
    0.63
     പേര
    0.56
     playbook
    0.56
     suss
    0.56
    น่า
    0.56
     څرنګوالی
    0.56
     seperate
    0.56
     (£
    0.55
    POSITIVE LOGITS
     Catalonia
    0.88
     gastronomy
    0.88
     pathologies
    0.87
     Catalan
    0.87
     Spain
    0.86
     tachycardia
    0.85
     Andalusia
    0.85
     coexistence
    0.83
     oncology
    0.81
     its
    0.80
    Act Density 0.010%

    No Known Activations