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

    Neuronpedia

    INDEX
    Explanations

    dialogue punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ക്കുകയും
    0.45
     nostri
    0.42
     මෙම
    0.42
     উহার
    0.41
    され
    0.40
     여러분
    0.39
     የሚ
    0.39
     yourselves
    0.39
     our
    0.39
     invokes
    0.39
    POSITIVE LOGITS
    他说
    0.76
    他說
    0.71
     “[
    0.68
     “‘
    0.68
     "[
    0.66
     “(
    0.65
    ：“
    0.64
    她说
    0.64
     "'
    0.63
     "...
    0.61
    Act Density 0.017%

    No Known Activations