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
    larınız
    1.29
     নিজে
    1.02
     নিজেই
    1.00
     Ihres
    0.97
    你也
    0.96
     usted
    0.95
     você
    0.93
     নিজেও
    0.93
     mógł
    0.88
     ćete
    0.87
    POSITIVE LOGITS
     ourselves
    2.56
    ಿದ್ದೇವೆ
    1.73
     نحن
    1.68
     আমাদের
    1.67
     можем
    1.64
     знаем
    1.61
     jsme
    1.59
     आहोत
    1.55
     pouvons
    1.53
     хотим
    1.52
    Act Density 0.227%

    No Known Activations