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

    Neuronpedia

    INDEX
    Explanations

    references to revisions or versions in texts

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

    rev followed by period or suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     princi
    -0.50
    mali
    -0.47
    matcher
    -0.47
    瘍
    -0.46
    Mice
    -0.46
    BAI
    -0.46
     Banker
    -0.46
    asio
    -0.46
     Idio
    -0.46
     Mice
    -0.45
    POSITIVE LOGITS
     rev
    1.91
     Rev
    1.84
    Rev
    1.84
    rev
    1.68
     REV
    1.60
    REV
    1.49
     revs
    1.28
     Revision
    0.96
     Revue
    0.93
     revision
    0.93
    Act Density 0.013%

    No Known Activations