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

    Neuronpedia

    INDEX
    Explanations

    the initial markers or indicators of a document, such as a start token

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

    Code, programming, or special characters

    np_acts-logits-general · gemini-2.0-flash

    special characters and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "):
    -0.49
    כח
    -0.48
     Land
    -0.48
    =[]
    -0.48
    ProductCategory
    -0.47
    ":
    -0.47
    PostId
    -0.46
    =[];
    -0.45
    CategoryId
    -0.45
    RoleId
    -0.45
    POSITIVE LOGITS
    $_['
    0.98
    IsContent
    0.94
    +#+#
    0.89
    MigrationBuilder
    0.84
    SourceChecksum
    0.83
    GEBURTSDATUM
    0.82
     Référence
    0.82
    Geplaatst
    0.81
    bitField
    0.78
     оригіналу
    0.76
    Act Density 0.095%

    No Known Activations