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

    Neuronpedia

    INDEX
    Explanations

    sentence endings, punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असल्याने
    0.66
     ngunit
    0.64
     असून
    0.63
     नसल्या
    0.63
     ಏಕೆಂದರೆ
    0.59
    ،
    0.59
     있으며
    0.57
     जिसमें
    0.55
     sehingga
    0.53
     ஆனால்
    0.51
    POSITIVE LOGITS
    。「
    0.69
    。“
    0.66
    。《
    0.66
    。
    0.59
    。『
    0.55
    .
    0.53
    ।
    0.45
    ‌.
    0.44
    ｡
    0.44
    တယ်။
    0.43
    Act Density 0.896%

    No Known Activations