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

    Neuronpedia

    INDEX
    Explanations

    academic subjects and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Edition
    0.77
     L
    0.74
    ్రహ్
    0.68
    izing
    0.66
     W
    0.65
     पेश
    0.63
     于
    0.61
     B
    0.61
    werks
    0.61
     Χ
    0.61
    POSITIVE LOGITS
    :
    1.10
    <unused1774>
    0.93
    ꗬ
    0.90
    <unused1699>
    0.88
    𒆞
    0.87
     راجسټ
    0.87
    ,:
    0.87
     अगेन
    0.86
    <unused1688>
    0.86
    <unused1709>
    0.85
    Act Density 0.001%

    No Known Activations