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

    Neuronpedia

    INDEX
    Explanations

    our and we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    1.52
     شما
    1.52
     você
    1.51
    you
    1.44
     vous
    1.37
     bạn
    1.34
    あなたは
    1.34
    你
    1.34
     আপনি
    1.25
    你在
    1.25
    POSITIVE LOGITS
     ourselves
    3.00
     nossas
    2.08
     our
    2.03
    我們的
    2.00
     nossos
    1.98
    我们的
    1.98
     우리의
    1.95
     nuestras
    1.94
     আমাদের
    1.93
     nuestros
    1.93
    Act Density 0.251%

    No Known Activations