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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities and numbers in a document

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

    "The" followed by certain nouns

    np_acts-logits-general · gemini-2.0-flash

    the followed by a specific noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.67
    rungsseite
    -0.62
     HttpNotFound
    -0.58
     numberWith
    -0.55
    Filmografie
    -0.55
     preſent
    -0.53
    WebElementEntity
    -0.52
     AssemblyVersion
    -0.51
     WebDriverWait
    -0.51
     följande
    -0.50
    POSITIVE LOGITS
     company
    0.64
    company
    0.53
     automaker
    0.51
     snippetHide
    0.47
    公司的
    0.46
     compan
    0.44
     increasingly
    0.42
    公司
    0.42
     firm
    0.41
     its
    0.41
    Act Density 0.625%

    No Known Activations