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

    Neuronpedia

    INDEX
    Explanations

    occurrences, questions, same nature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cartera
    0.45
     tasas
    0.43
     palust
    0.41
    典型的
    0.37
    شارات
    0.36
    ２
    0.36
     propensity
    0.35
     landfills
    0.35
     étaient
    0.35
     Ruhe
    0.35
    POSITIVE LOGITS
     тебе
    0.47
    ิ้ง
    0.47
     прямо
    0.45
    sning
    0.45
     நட்ப
    0.44
    Thread
    0.44
     тому
    0.42
    ที่จะ
    0.42
     tiếp
    0.42
     રીતે
    0.42
    Act Density 0.001%

    No Known Activations