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

    Neuronpedia

    INDEX
    Explanations

    People's Republic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SPREAD
    0.81
    城区
    0.76
     عل
    0.75
    tuple
    0.73
    관리
    0.72
     miejscowości
    0.71
     ಅಂ
    0.70
     Syst
    0.70
    𝑛
    0.70
    𝐗
    0.70
    POSITIVE LOGITS
     liberating
    1.07
     Liberation
    0.97
     liberation
    0.97
     Commiss
    0.93
     मुक्ति
    0.87
     livelihoods
    0.86
    解放
    0.85
     livelihood
    0.83
    检察
    0.80
     liberate
    0.78
    Act Density 0.006%

    No Known Activations