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

    Neuronpedia

    INDEX
    Explanations

    package manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    케
    0.26
    ред
    0.26
    ährung
    0.26
    ె
    0.25
    ন
    0.25
    nq
    0.24
    ﮕ
    0.24
    ﮯ
    0.24
    प्रकारे
    0.23
     linearized
    0.23
    POSITIVE LOGITS
    𝑟
    0.28
    𝑡
    0.28
    𝑢
    0.27
    𝑑
    0.26
    𝑚
    0.26
    Կ
    0.25
     Laat
    0.24
    zás
    0.24
    z
    0.24
    𝑛
    0.23
    Act Density 0.009%

    No Known Activations