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

    Neuronpedia

    INDEX
    Explanations

    police, crime, agents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nourishing
    0.83
     glycer
    0.82
     온도
    0.80
     bilayers
    0.79
     knitting
    0.79
     spacers
    0.78
    温度
    0.77
     aluminium
    0.76
     moisturizing
    0.76
     Collagen
    0.76
    POSITIVE LOGITS
     criminal
    1.95
     kriminal
    1.86
    criminal
    1.84
     police
    1.83
    riminal
    1.83
     policial
    1.82
     crime
    1.81
    Criminal
    1.81
    Police
    1.77
     Police
    1.77
    Act Density 0.681%

    No Known Activations