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

    Neuronpedia

    INDEX
    Explanations

    references to quantitative measurements or specifications

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

    immediately after "the" or "a"

    np_acts-logits-general · gemini-2.0-flash

    articles followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.64
     Wikimedijinoj
    -0.60
     Taktlose
    -0.53
    Jeografia
    -0.52
    цездатний
    -0.52
    djangoproject
    -0.51
     '\\;'
    -0.50
    يكب
    -0.50
     censiti
    -0.49
     Савезне
    -0.48
    POSITIVE LOGITS
     محفوظة
    0.44
     ferons
    0.39
     Độ
    0.38
    legungen
    0.38
    findpost
    0.38
     bezeichneter
    0.37
     visuel
    0.37
     the
    0.35
     prés
    0.35
    ImageIO
    0.35
    Act Density 2.438%

    No Known Activations