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

    Neuronpedia

    INDEX
    Explanations

    title and author metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     చర్చ
    0.46
     verá
    0.42
     către
    0.40
     podrás
    0.39
     эффек
    0.39
     ká
    0.38
    নাকে
    0.38
     Vocês
    0.37
     Eğer
    0.37
     vatandaş
    0.37
    POSITIVE LOGITS
     partly
    0.49
     OCLC
    0.44
     partially
    0.42
     chiefly
    0.42
    ︠
    0.41
     ;
    0.41
    ?,
    0.40
    -[
    0.40
     quarto
    0.40
     (?)
    0.39
    Act Density 0.003%

    No Known Activations