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

    Neuronpedia

    INDEX
    Explanations

    coding constructs related to testing and assertions in programming

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

    special characters and journal abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.96
     ModelExpression
    -0.83
     للاسماء
    -0.72
     CreateTagHelper
    -0.69
     springfox
    -0.68
    ValueGeneration
    -0.65
     HasFactory
    -0.65
    BeginContext
    -0.63
     noDo
    -0.62
     препратки
    -0.62
    POSITIVE LOGITS
    spyOn
    0.57
     
    0.37
    成
    0.35
    barkeit
    0.34
     process
    0.33
     Fre
    0.33
    -
    0.33
     (
    0.32
    ↵
    0.32
    ↵↵
    0.32
    Act Density 0.001%

    No Known Activations