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

    Neuronpedia

    INDEX
    Explanations

    place names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Это
    0.93
     Этот
    0.87
    Д
    0.85
     hindi
    0.85
     zem
    0.85
     Palestinians
    0.83
     الأرض
    0.80
     Jonah
    0.80
     quel
    0.79
     dure
    0.79
    POSITIVE LOGITS
    等地
    0.79
    tı
    0.78
    tions
    0.78
    tive
    0.75
    islava
    0.74
    town
    0.73
    ровка
    0.73
    ian
    0.72
    ța
    0.72
    proclaimed
    0.71
    Act Density 0.144%

    No Known Activations