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

    Neuronpedia

    INDEX
    Explanations

    we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yourself
    0.88
     сможете
    0.85
    your
    0.84
     kendini
    0.82
    yourself
    0.79
     anda
    0.79
    其
    0.79
    当你
    0.79
     নিজেই
    0.78
     আপনি
    0.78
    POSITIVE LOGITS
     ourselves
    1.66
     можем
    1.31
     allons
    1.26
     نحن
    1.26
     знаем
    1.25
     Ours
    1.22
    athers
    1.21
     talked
    1.21
     avons
    1.18
    eping
    1.18
    Act Density 0.259%

    No Known Activations