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

    Neuronpedia

    INDEX
    Explanations

    explain code line by line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     посредством
    0.46
    during
    0.39
    фу
    0.39
    हत
    0.39
    である
    0.38
     এতটাই
    0.38
    टक
    0.37
    immersive
    0.37
    ক্ষিত
    0.37
    ೇ
    0.36
    POSITIVE LOGITS
     aprend
    0.41
     potencialmente
    0.41
     potentially
    0.41
     möglicherweise
    0.41
     families
    0.40
     mungkin
    0.39
     çoğu
    0.38
     educ
    0.38
     unlike
    0.38
     Ethiopia
    0.38
    Act Density 0.013%

    No Known Activations