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
     গুলো
    0.36
    postion
    0.35
     WIFI
    0.34
     পরিক্ষ
    0.31
     बच्चो
    0.30
     जिसमे
    0.29
     অনুয
    0.29
     PHD
    0.29
     ‘’
    0.29
     সকল
    0.28
    POSITIVE LOGITS
     весьма
    0.37
     Presumably
    0.36
     offenbar
    0.35
     insofar
    0.34
     ziemlich
    0.33
    ஃப்
    0.33
     अपेक्षाकृत
    0.33
    学术
    0.32
     प्रॉब्ल
    0.32
     utterly
    0.32
    Act Density 0.007%

    No Known Activations