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

    Neuronpedia

    INDEX
    Explanations

    identifiers related to programming concepts and structures

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

    keys and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.94
    AndEndTag
    -0.94
    expandindo
    -0.63
    tagHelperRunner
    -0.60
    ParallelGroup
    -0.60
    AddTagHelper
    -0.59
    TagMode
    -0.59
    Hentet
    -0.59
    存于互联网档案馆
    -0.58
     ModelExpression
    -0.57
    POSITIVE LOGITS
     citoyens
    0.43
     Grecs
    0.39
     paille
    0.35
     Détails
    0.35
     accessibles
    0.35
     cathédrale
    0.34
     policiers
    0.33
    性和
    0.33
     citoy
    0.32
     toalla
    0.32
    Act Density 0.016%

    No Known Activations