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

    Neuronpedia

    INDEX
    Explanations

    government policy and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     因为
    0.74
     Holy
    0.67
     সেই
    0.65
     padre
    0.64
     Pleistocene
    0.63
     แต่
    0.61
     prophecy
    0.61
     sehr
    0.61
     volle
    0.61
     medan
    0.61
    POSITIVE LOGITS
    政策
    0.94
    government
    0.90
     कानूनों
    0.79
    정책
    0.79
    policy
    0.73
    措施
    0.73
     regulations
    0.73
    Government
    0.71
    0
    0.71
    legislation
    0.71
    Act Density 0.400%

    No Known Activations