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

    Neuronpedia

    INDEX
    Explanations

    police

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     governmental
    0.76
     officials
    0.74
     authorities
    0.72
     government
    0.71
     pemerintah
    0.71
     Officials
    0.70
    政府
    0.67
     gobierno
    0.67
     technicians
    0.65
    Officials
    0.65
    POSITIVE LOGITS
     Policing
    1.05
    Inspector
    1.05
     Inspector
    1.03
     policing
    1.02
     Polri
    0.96
     Insp
    0.93
     polici
    0.93
    警察
    0.93
    Insp
    0.92
     పోలీ
    0.91
    Act Density 0.032%

    No Known Activations