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

    Neuronpedia

    INDEX
    Explanations

    various punctuation and language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pods
    0.36
     niektórych
    0.35
     and
    0.35
     algumas
    0.35
     extreme
    0.34
     some
    0.34
     $
    0.34
     grazing
    0.34
     ELF
    0.33
     four
    0.33
    POSITIVE LOGITS
    ratulations
    0.46
    或其他
    0.42
    郆
    0.39
    usay
    0.38
     текста
    0.36
    <unused2138>
    0.36
     เงี้ย
    0.36
    之类的
    0.36
    <unused2199>
    0.36
    总之
    0.36
    Act Density 0.438%

    No Known Activations