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

    Neuronpedia

    INDEX
    Explanations

    numerator of fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IFT
    0.44
    。
    0.43
    并不
    0.41
    ۔
    0.40
    .
    0.40
     Taste
    0.39
    スポ
    0.38
    IF
    0.38
     In
    0.37
    NAME
    0.37
    POSITIVE LOGITS
     ανάπτυ
    0.45
    厲
    0.44
    পালের
    0.42
     ప్రస్తుతం
    0.42
     tableView
    0.41
    },\\
    0.41
     आगा
    0.40
     চম
    0.40
    ড়ান্ত
    0.39
     фай
    0.39
    Act Density 0.001%

    No Known Activations