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

    Neuronpedia

    INDEX
    Explanations

    colon symbols followed by numbers or variable identifiers

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

    code and markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.80
    OGND
    -0.76
     autorytatywna
    -0.75
    UserScript
    -0.75
     cherchés
    -0.74
    parsedMessage
    -0.73
    migrationBuilder
    -0.71
    <unused79>
    -0.70
    <unused8>
    -0.70
    [@BOS@]
    -0.70
    POSITIVE LOGITS
     <
    0.41
     =
    0.40
     [
    0.38
     ===
    0.36
    OVERR
    0.36
    !("{
    0.35
    ",
    0.35
    帖最后由
    0.35
     k
    0.35
    "
    0.34
    Act Density 0.012%

    No Known Activations