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

    Neuronpedia

    INDEX
    Explanations

    overall leadership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alumin
    0.70
    ંજ
    0.65
     clippings
    0.62
    ពណ៌
    0.61
     affez
    0.60
     মরদেহ
    0.60
    ത്തിന
    0.59
    ത്ര
    0.59
     crackers
    0.58
    Equatable
    0.57
    POSITIVE LOGITS
     leadership
    2.52
     Leadership
    2.28
     leader
    2.24
    Leadership
    2.23
     liderazgo
    2.16
     leaders
    2.14
    leadership
    2.10
     management
    2.00
     Leaders
    1.98
     Leader
    1.95
    Act Density 1.002%

    No Known Activations