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

    Neuronpedia

    INDEX
    Explanations

    * **Example, Clear, Clarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     구현
    0.88
    வும்
    0.86
    собенности
    0.86
     now
    0.83
     ታ
    0.83
     इसने
    0.83
    अब
    0.83
     अब
    0.81
     dimost
    0.81
    এখন
    0.80
    POSITIVE LOGITS
     ενη
    0.68
     luận
    0.68
     उल्लेख
    0.62
    谥
    0.61
    ారె
    0.61
     pretty
    0.61
     নামকরণ
    0.60
     copy
    0.60
     copyright
    0.60
    gitignore
    0.60
    Act Density 0.219%

    No Known Activations