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

    Neuronpedia

    INDEX
    Explanations

    international and global affairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    全国
    0.86
    Welt
    0.83
    全國
    0.81
     Welt
    0.77
     weltweit
    0.75
     nacionais
    0.73
     statewide
    0.73
    welt
    0.73
     전국
    0.72
    LOCAL
    0.72
    POSITIVE LOGITS
    ized
    1.13
    ist
    0.96
    化的
    0.94
    范围内
    0.93
    ização
    0.93
    izzazione
    0.91
    ización
    0.89
    isering
    0.87
    ization
    0.85
    IZATION
    0.84
    Act Density 0.100%

    No Known Activations