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

    Neuronpedia

    INDEX
    Explanations

    sections of text that are heavily commented or contain documentation-like content

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

    code documentation and inline comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.91
     autorytatywna
    -0.89
    featureID
    -0.83
    Personensuche
    -0.82
     otomatig
    -0.80
    ➟
    -0.79
    GEBURTSDATUM
    -0.77
    ьаж
    -0.75
    ſt
    -0.74
     فريبيس
    -0.73
    POSITIVE LOGITS
     the
    0.35
     process
    0.34
    subsection
    0.33
    0.32
     test
    0.31
     appropriate
    0.31
     yle
    0.31
    process
    0.30
     check
    0.29
     Beim
    0.28
    Act Density 0.002%
    No Known Activations