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
     police
    0.95
     Royal
    0.94
     Police
    0.93
    Police
    0.91
    Royal
    0.89
     पोलीस
    0.82
    police
    0.82
    警察
    0.81
     politie
    0.78
     पोलिसा
    0.75
    POSITIVE LOGITS
    patched
    0.73
    움을
    0.73
     millet
    0.72
     원
    0.70
     स्टैंड
    0.68
     trest
    0.67
     интересу
    0.66
     парни
    0.66
     пределах
    0.65
     pat
    0.64
    Act Density 0.010%

    No Known Activations