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

    Neuronpedia

    INDEX
    Explanations

    economic and policy terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    流畅
    0.48
    的感觉
    0.47
    这个
    0.46
     Bitmap
    0.46
    杨
    0.46
    场景
    0.46
    图形
    0.46
     یاد
    0.45
    变形
    0.45
     Atual
    0.44
    POSITIVE LOGITS
     subsidies
    0.80
     monopolies
    0.66
     pensions
    0.64
     taxation
    0.62
     wage
    0.61
     quotas
    0.60
     tax
    0.59
     exemptions
    0.59
     lobbying
    0.58
     subsidy
    0.57
    Act Density 0.031%

    No Known Activations