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

    Neuronpedia

    INDEX
    Explanations

    multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     *>
    0.35
    ​)
    0.34
     l
    0.33
     \
    0.33
    OCE
    0.33
     vies
    0.32
    ​​​​
    0.32
     مت
    0.32
    strings
    0.32
     V
    0.31
    POSITIVE LOGITS
    ុស
    0.43
    getDay
    0.41
    ሃኒ
    0.39
    ,((
    0.38
     nuovi
    0.37
    এদিকে
    0.37
    燡
    0.37
     quieran
    0.37
     प्रूव
    0.37
     pourraient
    0.37
    Act Density 0.367%

    No Known Activations