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

    Neuronpedia

    INDEX
    Explanations

    question endings or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     என்பவர்
    0.37
     General
    0.35
     Sad
    0.35
     ...)
    0.35
    /=
    0.33
     પટે
    0.33
    れません
    0.32
     ..."
    0.32
     Osten
    0.32
    0.32
    POSITIVE LOGITS
    !
    0.80
    ။
    0.74
    ។
    0.69
     :)
    0.67
    ！
    0.66
    ۔
    0.65
     🙂
    0.64
    。
    0.64
    ؟
    0.64
    ।
    0.63
    Act Density 0.015%

    No Known Activations