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

    Neuronpedia

    INDEX
    Explanations

    currency and date ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lacked
    0.27
     hadn
    0.27
     নেয়া
    0.27
     generalizes
    0.27
    或者是
    0.26
     quei
    0.26
     Commencez
    0.26
     ponencia
    0.25
     préalable
    0.25
    uyi
    0.25
    POSITIVE LOGITS
    到
    0.35
    까지
    0.35
     the
    0.34
    hingga
    0.34
    直至
    0.34
     ድረስ
    0.34
     sampai
    0.33
     hasta
    0.32
     পর্যন্ত
    0.32
    まで
    0.31
    Act Density 0.157%

    No Known Activations