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

    Neuronpedia

    INDEX
    Explanations

    code blocks and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    增长
    0.41
    :":
    0.41
    Ầ
    0.37
    ็บ
    0.37
    低于
    0.37
    )：
    0.36
    不
    0.36
    ：“
    0.36
    ំន
    0.35
    েরও
    0.35
    POSITIVE LOGITS
    𝗲
    0.42
     diez
    0.42
     sech
    0.42
    are
    0.40
    ijs
    0.40
    ሚያ
    0.40
    ли
    0.40
    ке
    0.39
    ное
    0.39
     خمسه
    0.38
    Act Density 0.027%

    No Known Activations