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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     তারপর
    0.35
     최대한
    0.31
    䂘
    0.30
     అమలు
    0.30
    จำ
    0.29
     erbjud
    0.29
     matern
    0.29
     сі
    0.29
    ቻል
    0.29
     baddies
    0.29
    POSITIVE LOGITS
     questions
    0.41
     Questions
    0.39
     pertanyaan
    0.39
     hỏi
    0.38
     pergunt
    0.38
    ask
    0.38
     inquiries
    0.37
     vragen
    0.36
    asked
    0.36
     Fragen
    0.36
    Act Density 0.181%

    No Known Activations