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

    Neuronpedia

    INDEX
    Explanations

    police and policing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    开发者
    0.54
     ডেভেল
    0.52
     ઉત્પાદ
    0.51
     Developer
    0.50
     marketer
    0.48
     Figma
    0.47
     HubSpot
    0.47
     주인
    0.46
     Developers
    0.46
     Bibliothèque
    0.46
    POSITIVE LOGITS
     police
    1.70
    police
    1.58
     Police
    1.55
    Police
    1.55
     полицей
    1.52
     경찰
    1.45
     patrol
    1.43
    警察
    1.43
     polizia
    1.40
     policiais
    1.40
    Act Density 0.027%

    No Known Activations