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

    Neuronpedia

    INDEX
    Explanations

    police officers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.72
    u
    0.63
    as
    0.62
     Forests
    0.60
     Рас
    0.56
     Sakai
    0.56
    atac
    0.55
     Puig
    0.54
     Networks
    0.52
     Haci
    0.52
    POSITIVE LOGITS
    police
    1.02
     police
    1.02
    ตำรวจ
    0.93
     경찰
    0.86
     policemen
    0.85
     полицей
    0.84
     policeman
    0.83
    Police
    0.82
    पुलिस
    0.79
     полиции
    0.79
    Act Density 0.015%

    No Known Activations