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

    Neuronpedia

    INDEX
    Explanations

    multilingual context with facts and predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ។
    0.22
    ・
    0.20
    を
    0.20
    .[
    0.20
    ları
    0.19
    và
    0.18
    larım
    0.18
     你
    0.18
     থেকে
    0.18
     হিসেবে
    0.18
    POSITIVE LOGITS
     쉽게
    0.26
     어떻게
    0.26
     더욱
    0.24
     단순히
    0.23
     점점
    0.23
    積極的に
    0.23
     새로운
    0.23
     제대로
    0.22
     എങ്ങനെ
    0.21
     지금까지
    0.21
    Act Density 0.008%

    No Known Activations