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

    Neuronpedia

    INDEX
    Explanations

    labels and identifiers in code contexts

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

    Tokens related to titles or names

    np_acts-logits-general · gemini-2.0-flash

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.52
    jsdelivr
    -0.51
    发表于
    -0.49
    ventude
    -0.48
     cast
    -0.47
    statusCode
    -0.46
    cast
    -0.46
     numbers
    -0.46
     استنادى
    -0.46
    RoleId
    -0.46
    POSITIVE LOGITS
     name
    1.05
     title
    1.00
     getName
    0.95
     Name
    0.94
     productName
    0.93
    title
    0.92
     NAME
    0.91
    name
    0.89
     getTitle
    0.89
     titles
    0.88
    Act Density 0.159%

    No Known Activations