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

    Neuronpedia

    INDEX
    Explanations

    mentions of holidays or events

    oai_token-act-pair · gemini-2.0-flash

    holidays

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FetchType
    -0.64
     initComponents
    -0.59
    onViewCreated
    -0.55
    readObject
    -0.55
    ThroughAttribute
    -0.55
    sizeCache
    -0.54
     متحده
    -0.54
     AssemblyProduct
    -0.54
    nonatomic
    -0.52
    Werke
    -0.52
    POSITIVE LOGITS
     holiday
    1.72
     Christmas
    1.71
     holidays
    1.70
     Thanksgiving
    1.53
     christmas
    1.47
    Christmas
    1.45
     Holiday
    1.43
     Xmas
    1.43
     Halloween
    1.38
    holiday
    1.38
    Act Density 2.783%

    No Known Activations