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

    Neuronpedia

    INDEX
    Explanations

    may have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sType
    1.30
    '></
    1.24
    satz
    1.20
    tions
    1.19
    تنا
    1.13
    sn
    1.13
     `>`,
    1.10
    াচ্ছে
    1.09
    тическая
    1.08
    tedir
    1.05
    POSITIVE LOGITS
    il
    1.34
    r
    1.28
    ag
    1.26
    m
    1.21
    ㅎ
    1.18
    റു
    1.15
    Υ
    1.14
    স্ট
    1.13
     quarant
    1.13
     mediocr
    1.13
    Act Density 0.027%

    No Known Activations