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

    Neuronpedia

    INDEX
    Explanations

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    čiť
    0.32
     fundamentales
    0.30
     možno
    0.30
    újt
    0.30
     trú
    0.30
     మరి
    0.29
     」
    0.29
    鈿
    0.29
    дер
    0.29
     ಕೂ
    0.29
    POSITIVE LOGITS
    そのため
    0.36
    although
    0.31
    Although
    0.30
     although
    0.30
    ,
    0.30
     б
    0.29
     compared
    0.29
     Pess
    0.29
     um
    0.29
     Similarly
    0.29
    Act Density 0.112%

    No Known Activations