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

    Neuronpedia

    INDEX
    Explanations

    historical or fantasy war stories, potentially mentioning acts of violence or terror

    oai_token-act-pair · gemini-2.0-flash

    violence/aggression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.61
     snippetHide
    -0.61
    CloseOperation
    -0.60
     JpaRepository
    -0.60
     CreateTagHelper
    -0.59
    ReusableCell
    -0.56
    viewDidLoad
    -0.55
    Conclusie
    -0.55
    gyz
    -0.54
    XmlAccessorType
    -0.54
    POSITIVE LOGITS
    <bos>
    1.33
    “
    0.59
    ‘
    0.50
    '
    0.50
    "
    0.48
    |
    0.46
    #
    0.46
    <
    0.45
    Op
    0.45
    [
    0.44
    Act Density 7.510%

    No Known Activations