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

    Neuronpedia

    INDEX
    Explanations

    references to medical records and regulations

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

    Comes before punctuation

    np_acts-logits-general · gemini-2.0-flash

    specific nouns or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.25
    DockStyle
    -1.22
     ་་
    -1.12
    NUMX
    -1.09
    tagHelperRunner
    -1.06
    awtextra
    -1.04
     مرئيه
    -1.03
    ruptedException
    -1.03
     CascadeType
    -1.02
    AndEndTag
    -0.98
    POSITIVE LOGITS
    ↵↵
    1.50
    :
    1.29
    ↵
    1.20
    ↵↵↵
    1.19
    ?
    1.18
    !
    1.05
    <eos>
    1.00
    ?:
    0.98
    ↵↵↵↵
    0.98
    .
    0.88
    Act Density 1.073%

    No Known Activations