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

    Neuronpedia

    INDEX
    Explanations

    formal citations and references in academic text

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

    citation numbers in brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strá
    -0.43
     Italijani
    -0.43
    djangoproject
    -0.37
     Rückseite
    -0.35
     استنادى
    -0.32
     Heimat
    -0.31
     gobiernos
    -0.30
     collectivités
    -0.30
     innego
    -0.29
     Altstadt
    -0.28
    POSITIVE LOGITS
     للمعارف
    0.79
    OGND
    0.75
    TagMode
    0.73
     EconPapers
    0.66
     otomatig
    0.62
    Personensuche
    0.59
     surla
    0.54
     ferons
    0.50
     gyhoeddwyd
    0.50
    windowFixed
    0.50
    Act Density 0.009%

    No Known Activations