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

    Neuronpedia

    INDEX
    Explanations

    words related to children's activities like reading or story telling, combined with words about books and fairy tales.

    oai_token-act-pair · gemini-2.0-flash

    story

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.86
     Савезне
    -0.74
     виправивши
    -0.72
    AddTagHelper
    -0.69
    OGND
    -0.69
    -0.67
    DispatchToProps
    -0.65
     كومونز
    -0.64
    Билгалдахарш
    -0.64
    setVerticalGroup
    -0.64
    POSITIVE LOGITS
     story
    1.38
     stories
    1.32
    Story
    1.23
    Stories
    1.22
    stories
    1.22
     Story
    1.20
    story
    1.18
     STORY
    1.14
     Stories
    1.13
     read
    1.11
    Act Density 1.141%

    No Known Activations