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

    Neuronpedia

    INDEX
    Explanations

    code blocks and inline code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    quiera
    1.82
    ন্যাশনাল
    1.76
     rende
    1.70
    р
    1.65
    ंशिक
    1.64
     stof
    1.64
     xhr
    1.59
     peces
    1.58
     |--
    1.52
    aneously
    1.52
    POSITIVE LOGITS
    i
    2.54
    י
    2.44
    ی
    2.40
    𝑡
    2.21
    𝑖
    2.20
    ties
    2.17
    क
    2.10
    te
    2.09
     adage
    2.06
    בּ
    1.99
    Act Density 0.416%

    No Known Activations