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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and coding practices

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

    many items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.56
     EconPapers
    -0.55
    Autoritní
    -0.54
    NgModule
    -0.50
     betweenstory
    -0.49
     Italijanski
    -0.48
     '\\;'
    -0.47
    RuleContext
    -0.47
    riwal
    -0.46
    actionMode
    -0.46
    POSITIVE LOGITS
     many
    1.22
     многих
    1.06
    many
    1.02
    Many
    1.02
     Many
    1.01
     meisten
    1.00
    多くの
    1.00
     some
    0.96
     некоторых
    0.95
     многие
    0.94
    Act Density 0.176%

    No Known Activations