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

    Neuronpedia

    INDEX
    Explanations

    row, col coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xF3>
    1.43
     библиоте
    1.30
     библиотеки
    1.21
     библиотека
    1.12
     всем
    1.12
    部长
    1.11
    芸
    1.09
    لیت
    1.08
     (
    1.08
     (_
    1.08
    POSITIVE LOGITS
     ſ
    1.21
     Faktoren
    1.19
     fatores
    1.17
    \%,
    1.11
     Hing
    1.08
    𝗢
    1.08
     Cret
    1.08
    öne
    1.07
     Quindi
    1.07
    ᧐
    1.06
    Act Density 0.006%

    No Known Activations