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

    Neuronpedia

    INDEX
    Explanations

    identifiers and keys in database schema or programming contexts

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

    identifier: or identifier |

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasAnnotation
    -0.59
     OMITBAD
    -0.58
    issory
    -0.57
    󠁴
    -0.57
    UnsafeEnabled
    -0.56
    hyrchwyd
    -0.54
    aarrggbb
    -0.54
     esternos
    -0.54
     gyhoeddwyd
    -0.54
    rouvez
    -0.53
    POSITIVE LOGITS
     offer
    0.38
     Offer
    0.34
     Unger
    0.32
     Deane
    0.31
     contract
    0.31
     capacity
    0.30
     liten
    0.30
     pattes
    0.30
     tavola
    0.30
     halbe
    0.29
    Act Density 0.002%

    No Known Activations