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

    Neuronpedia

    INDEX
    Explanations

    societal and economic transformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.81
    A
    0.70
    S
    0.66
    تبه
    0.63
    k
    0.63
    Deck
    0.60
     ని
    0.59
    kyl
    0.57
    ം
    0.57
    ان
    0.56
    POSITIVE LOGITS
    0.61
    revolution
    0.57
    зация
    0.56
    ization
    0.55
     revolución
    0.55
     urbanization
    0.55
     उन्होंने
    0.54
     fatta
    0.54
     privatization
    0.53
     Yugoslavia
    0.51
    Act Density 0.111%

    No Known Activations