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

    Neuronpedia

    INDEX
    Explanations

    formal introductions and the proper etiquette surrounding them

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

    introductions and reporting information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voorzien
    -0.41
    -0.40
    tagHelperRunner
    -0.40
    ArrowToggle
    -0.38
     EconPapers
    -0.37
     الرياضيه
    -0.34
    ngdoc
    -0.34
    новниш
    -0.34
     <>",
    -0.34
     kasarigan
    -0.34
    POSITIVE LOGITS
    XmlType
    0.47
     artic
    0.44
    ArgsConstructor
    0.44
    SourceChecksum
    0.44
     accol
    0.44
     clams
    0.43
    artic
    0.43
     cla
    0.43
    ScopeManager
    0.43
     clapping
    0.42
    Act Density 0.048%

    No Known Activations