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

    Neuronpedia

    INDEX
    Explanations

    numbers and days, smaller than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    មា
    0.43
    همه
    0.43
     veřej
    0.42
    送料無料
    0.40
    ꯌ
    0.39
    ፈላ
    0.38
    GEBURTSORT
    0.37
     வெவ்வேறு
    0.37
    féle
    0.37
     FormGroup
    0.35
    POSITIVE LOGITS
     dando
    0.39
     আসতে
    0.37
     ২৬
    0.36
     alkan
    0.35
    Dto
    0.35
    我都
    0.35
    ==============
    0.35
    typedef
    0.34
     ২৫
    0.34
    didn
    0.34
    Act Density 0.131%

    No Known Activations