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

    Neuronpedia

    INDEX
    Explanations

    the words "riding", "ators", "bike", and similar words

    oai_token-act-pair · gemini-2.0-flash

    riding, activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '
    -0.72
     l
    -0.68
     `
    -0.60
     ‘
    -0.59
    <eos>
    -0.57
    ↵
    -0.57
    se
    -0.56
    le
    -0.55
     non
    -0.53
     
    -0.52
    POSITIVE LOGITS
    RenderAtEndOf
    1.34
     مرئيه
    1.30
    DockStyle
    1.30
     EconPapers
    1.23
     $_"
    1.20
     myſelf
    1.17
     Efq
    1.17
    contentLoaded
    1.16
    PerformLayout
    1.16
     يتيمه
    1.15
    Act Density 0.624%

    No Known Activations