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

    Neuronpedia

    INDEX
    Explanations

    government ministers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    1.16
     was
    1.16
    ant
    1.13
    ian
    1.09
     you
    1.07
    ul
    0.98
    ne
    0.95
    这
    0.93
     кора
    0.91
     an
    0.91
    POSITIVE LOGITS
     Ministers
    0.97
     وزير
    0.92
    قي
    0.91
    Minister
    0.88
    ված
    0.88
    Minist
    0.87
    ווי
    0.86
     Minister
    0.86
    وک
    0.84
    ющих
    0.83
    Act Density 0.003%

    No Known Activations