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

    Neuronpedia

    INDEX
    Explanations

    format specifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pyrimidine
    0.31
    جميع
    0.29
    สื่อ
    0.29
     иллю
    0.28
     капита
    0.27
    ്രീ
    0.27
    ПО
    0.27
    🤥
    0.27
    Seite
    0.26
     ஊழிய
    0.26
    POSITIVE LOGITS
     Similarly
    0.33
     other
    0.31
     altra
    0.29
     another
    0.29
     similarly
    0.28
     másik
    0.28
    另一个
    0.28
     otro
    0.28
     Stone
    0.27
     its
    0.27
    Act Density 0.581%

    No Known Activations