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

    Neuronpedia

    INDEX
    Explanations

    words that are descriptive and are related to the physical world.

    oai_token-act-pair · gemini-2.0-flash

    sports and environmental conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :+:
    -0.59
    ╗
    -0.56
    HomeAsUpEnabled
    -0.55
    giver
    -0.53
    gridx
    -0.52
    ρίες
    -0.52
    Grüße
    -0.51
     dessinée
    -0.51
    UnusedPrivate
    -0.51
    AdapterFactory
    -0.51
    POSITIVE LOGITS
    verwijspagina
    0.65
     <=",
    0.59
     situation
    0.53
     estimés
    0.53
     deepcopy
    0.52
    تج
    0.52
    matchCondition
    0.51
    NamedQueries
    0.50
    PropertyGroup
    0.48
     CreateTagHelper
    0.48
    Act Density 3.530%

    No Known Activations