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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives and sentiment.

    oai_token-act-pair · gemini-2.0-flash

    great

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.70
     myſelf
    -0.68
     itſelf
    -0.68
     chofe
    -0.64
    awtextra
    -0.64
    ISupport
    -0.62
    TypedDataSet
    -0.62
    tvguidetime
    -0.61
    setVerticalGroup
    -0.61
     Efq
    -0.61
    POSITIVE LOGITS
    ly
    0.50
    StoryboardSegue
    0.50
     brand
    0.49
    IVE
    0.48
     kasarigan
    0.47
    INIT
    0.47
     يتيمه
    0.46
     contrast
    0.44
    █
    0.44
     number
    0.44
    Act Density 10.495%

    No Known Activations