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

    Neuronpedia

    INDEX
    Explanations

    this allows it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bằng
    0.55
     çünkü
    0.46
     dengan
    0.46
     увеличить
    0.46
     যেহেতু
    0.45
     vanwege
    0.44
     avec
    0.43
    ជាមួយនឹង
    0.43
     থাকলে
    0.42
     poprzez
    0.42
    POSITIVE LOGITS
     this
    0.55
     هذا
    0.50
    this
    0.45
     suitability
    0.45
     ranks
    0.43
     unrival
    0.43
    Conclusion
    0.41
     unlike
    0.41
    unlike
    0.41
    适合
    0.41
    Act Density 0.250%

    No Known Activations