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

    Neuronpedia

    INDEX
    Explanations

    measures of agreement or reliability in data

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

    inter rater reliability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vorbe
    -0.39
    uminense
    -0.38
     picioare
    -0.38
     Smal
    -0.37
     Bro
    -0.35
     epic
    -0.35
     économ
    -0.35
    JAMIN
    -0.35
     cose
    -0.35
     BOMB
    -0.34
    POSITIVE LOGITS
     للمعارف
    0.54
    ViewImports
    0.54
    addCriterion
    0.53
    ScopeManager
    0.51
    +#+#
    0.50
     дописавши
    0.49
    TagMode
    0.48
    verwijspagina
    0.48
     Catawiki
    0.46
     disambiguazione
    0.46
    Act Density 0.802%

    No Known Activations