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

    Neuronpedia

    INDEX
    Explanations

    we're or we have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     me
    1.59
    私は
    1.57
     আমাকে
    1.46
    给我
    1.43
     আমি
    1.41
    給我
    1.40
     எனக்கு
    1.38
     मुझे
    1.36
     мне
    1.33
    私の
    1.32
    POSITIVE LOGITS
     ourselves
    3.76
     можем
    2.71
     знаем
    2.60
     хотим
    2.58
     nuestras
    2.48
     our
    2.42
    我们的
    2.40
     chúng
    2.40
     છીએ
    2.38
     nossos
    2.37
    Act Density 0.259%

    No Known Activations