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

    Neuronpedia

    INDEX
    Explanations

    names of authors and their affiliations in academic citations

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

    proper nouns separated by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     køb
    -0.37
     zostać
    -0.35
     gemäß
    -0.35
    NextPage
    -0.35
     inden
    -0.35
     według
    -0.34
    olon
    -0.34
     jedes
    -0.34
     still
    -0.33
     görü
    -0.33
    POSITIVE LOGITS
    SourceChecksum
    0.65
    ьаж
    0.62
     '\\;'
    0.58
     <>",
    0.56
    MLLoader
    0.55
    RegressionTest
    0.54
    autaire
    0.52
     يتيمه
    0.50
     Seeder
    0.49
     Changer
    0.49
    Act Density 0.030%

    No Known Activations