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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    (INCLUDING, BUT NOT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     physical
    -0.36
     hundreds
    -0.36
     driver
    -0.32
     size
    -0.32
    driver
    -0.31
    boks
    -0.31
    author
    -0.30
    上
    -0.30
     regel
    -0.30
     author
    -0.30
    POSITIVE LOGITS
     للمعارف
    0.75
     kasarigan
    0.75
    KommentareTeilen
    0.69
     autorytatywna
    0.69
     يتيمه
    0.67
    lapsingToolbar
    0.65
     '\\;'
    0.65
     nahilalakip
    0.65
    XmlAccessType
    0.63
    StoryboardSegue
    0.63
    Act Density 0.003%

    No Known Activations