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

    Neuronpedia

    INDEX
    Explanations

    worker and workplace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oretically
    0.52
    n
    0.46
    тся
    0.45
    limit
    0.44
    barkeit
    0.42
    ంక
    0.42
    ㌔
    0.42
    siniz
    0.42
    nahme
    0.40
    ladı
    0.40
    POSITIVE LOGITS
     marav
    0.46
    যজ্ঞ
    0.45
    आर
    0.45
    ជាមួយ
    0.44
     they
    0.42
     competing
    0.41
    और
    0.40
     ashore
    0.40
     दैट
    0.40
     and
    0.40
    Act Density 0.446%

    No Known Activations