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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᔾ
    0.44
    ंदरे
    0.43
    0.41
    㸵
    0.41
    让人
    0.41
    上涨
    0.41
    🠀
    0.41
    0.40
    缫
    0.40
    <unused681>
    0.40
    POSITIVE LOGITS
    .
    0.53
     \
    0.53
    _
    0.46
    _{
    0.46
    0.45
    _{\
    0.45
    (
    0.44
    '
    0.44
    {\
    0.44
     (
    0.43
    Act Density 0.039%

    No Known Activations