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

    Neuronpedia

    INDEX
    Explanations

    detective and police work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Police
    0.95
    Police
    0.94
    police
    0.89
     полицей
    0.86
     police
    0.84
     पुलिस
    0.82
     پولیس
    0.81
    पुलिस
    0.79
     policial
    0.79
     policiais
    0.79
    POSITIVE LOGITS
     plain
    0.45
     units
    0.44
     Midtown
    0.44
     bomb
    0.43
     bombs
    0.43
     undercover
    0.42
     intra
    0.42
     morals
    0.42
     narcotics
    0.42
     bombas
    0.42
    Act Density 0.009%

    No Known Activations