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

    Neuronpedia

    INDEX
    Explanations

    probability calculations

    np_max-act · gemini-2.0-flash

    probability-related phrases and terms involving letter combinations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Drupal
    -0.07
     Piper
    -0.06
     أ
    -0.06
     ATTR
    -0.06
    _OW
    -0.06
    .executeQuery
    -0.06
    wart
    -0.06
    gMaps
    -0.06
     cuanto
    -0.06
     subsection
    -0.06
    POSITIVE LOGITS
    (Name
    0.07
    astype
    0.07
     号
    0.06
     commodities
    0.06
    样的
    0.06
    Trait
    0.06
    orget
    0.06
     eaten
    0.06
     tens
    0.06
     are
    0.06
    Act Density 0.001%

    No Known Activations