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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives combined with "a"

    oai_token-act-pair · gemini-2.0-flash

    Programming keywords

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propOrder
    -0.71
    ActionCreators
    -0.65
    icago
    -0.54
     Hard
    -0.53
    вку
    -0.50
    manteau
    -0.50
    IndentedString
    -0.50
     متعلقه
    -0.49
     schuld
    -0.47
     confiance
    -0.46
    POSITIVE LOGITS
    djangoproject
    0.67
    новништво
    0.66
     utafitiHapana
    0.56
    Gweler
    0.56
    HttpServlet
    0.55
    itinéraire
    0.54
    日閲覧
    0.51
     BoxDecoration
    0.50
     localObject
    0.50
    abstractmethod
    0.49
    Act Density 2.301%

    No Known Activations