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

    Neuronpedia

    INDEX
    Explanations

    international + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दुनिया
    0.48
     दुनियाभर
    0.47
     wereld
    0.46
    বিশ্ব
    0.46
    世界
    0.46
     ен
    0.44
     elettron
    0.44
     є
    0.43
     irres
    0.43
     двадцать
    0.43
    POSITIVE LOGITS
    象棋
    0.58
     Relations
    0.51
     Bac
    0.46
    isering
    0.43
     relations
    0.42
    Relations
    0.42
    escu
    0.41
    relations
    0.39
     القانون
    0.39
     Narcotics
    0.39
    Act Density 0.004%

    No Known Activations