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

    Neuronpedia

    INDEX
    Explanations

    limited government intervention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাংলাদেশকে
    0.39
    épend
    0.39
    缝
    0.38
     dham
    0.38
    UCLEAR
    0.38
     anatomic
    0.38
    뀌
    0.37
     addObject
    0.37
    改革
    0.37
     गुणनखंड
    0.37
    POSITIVE LOGITS
     centralized
    0.79
     intervention
    0.77
     centrally
    0.75
     paternal
    0.73
     statist
    0.71
     intrusive
    0.69
     Intervention
    0.67
     infring
    0.67
     collect
    0.66
     bureaucr
    0.66
    Act Density 0.016%

    No Known Activations