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

    Neuronpedia

    INDEX
    Explanations

    foreign conjunctions and adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DIY
    0.45
    !"
    0.43
     FAQs
    0.42
     nM
    0.42
    \\'
    0.40
    \'
    0.40
     SaaS
    0.40
    丨
    0.39
     শিগ
    0.39
     eBook
    0.38
    POSITIVE LOGITS
    都已经
    0.57
    件事情
    0.56
    នៅក្នុង
    0.55
    並且
    0.54
    并且
    0.53
    或者是
    0.52
     యొక్క
    0.51
    就已经
    0.51
    그리고
    0.50
    बहुत
    0.50
    Act Density 0.008%

    No Known Activations