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

    Neuronpedia

    INDEX
    Explanations

    the word "not"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Exper
    -0.56
    Kenn
    -0.55
    RIQUE
    -0.53
    amling
    -0.50
     fal
    -0.49
     Huy
    -0.48
    exper
    -0.48
    igue
    -0.48
     Händ
    -0.47
     Subject
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.89
    CloseOperation
    0.86
    tagHelperRunner
    0.81
     Seeder
    0.78
    NameInMap
    0.77
    IsContent
    0.75
    RetentionPolicy
    0.74
    RenderAtEndOf
    0.74
    XmlSchema
    0.73
    RectangleBorder
    0.73
    Act Density 0.001%

    No Known Activations