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

    Neuronpedia

    INDEX
    Explanations

    modulate, disrupt, promote, suppress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    health
    0.95
     Health
    0.91
    สุขภาพ
    0.90
     здоровья
    0.90
    Health
    0.88
     здоровье
    0.88
     health
    0.86
     kesehatan
    0.81
    HEALTH
    0.78
     Gesundheits
    0.76
    POSITIVE LOGITS
     interacts
    1.10
     interfere
    1.06
     interferes
    1.04
     Interference
    1.04
     interfering
    1.02
     modulate
    1.00
     modulates
    0.98
     disrupts
    0.97
     modulating
    0.95
     modifying
    0.94
    Act Density 0.122%

    No Known Activations