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

    Neuronpedia

    INDEX
    Explanations

    governance and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jemand
    0.80
    한국
    0.79
     робо
    0.75
     ro
    0.73
     نیوز
    0.71
     україн
    0.70
     преди
    0.69
    Italia
    0.68
     япон
    0.68
     giapp
    0.67
    POSITIVE LOGITS
    ycles
    0.65
     Abroad
    0.61
    팎
    0.60
     स्थानांतरित
    0.59
    绛
    0.58
    कतों
    0.57
     निर्यात
    0.57
    checks
    0.56
    AppBsky
    0.56
    ordinated
    0.55
    Act Density 0.893%

    No Known Activations