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

    Neuronpedia

    INDEX
    Explanations

    Russian text or code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.47
     eficiente
    0.44
    ಫ್
    0.44
    抨
    0.44
     participan
    0.42
    !\
    0.42
    \
    0.42
     petting
    0.41
    ఫ్‌
    0.41
     abstractions
    0.40
    POSITIVE LOGITS
    semibold
    0.48
    is
    0.46
    prints
    0.45
    േഖ
    0.44
    𝗻
    0.43
    became
    0.41
    н
    0.41
    text
    0.40
    has
    0.40
    us
    0.39
    Act Density 0.006%

    No Known Activations