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

    Neuronpedia

    INDEX
    Explanations

    future of work and automation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     финансовых
    0.57
     финансо
    0.56
     влияния
    0.56
     финанси
    0.53
    影响
    0.52
     영향
    0.52
     влия
    0.52
     прогно
    0.51
     trends
    0.50
     정부
    0.50
    POSITIVE LOGITS
     productivity
    0.56
     worker
    0.53
    worker
    0.52
    技能
    0.52
     Aufgabe
    0.51
    productivity
    0.51
     skill
    0.51
    スキル
    0.49
     Productivity
    0.47
     configure
    0.47
    Act Density 0.144%

    No Known Activations