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

    Neuronpedia

    INDEX
    Explanations

    structured data in a technical or computational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    UI elements or code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     some
    -0.33
     honra
    -0.33
     fire
    -0.30
     cha
    -0.28
     honor
    -0.27
     pin
    -0.27
     brû
    -0.27
     original
    -0.27
    SignOut
    -0.27
     sem
    -0.26
    POSITIVE LOGITS
    PerformLayout
    0.84
    sizeCache
    0.82
    aarrggbb
    0.81
    transQ
    0.80
     IBOutlet
    0.78
    AsUp
    0.75
    exitRule
    0.75
    RenderAtEndOf
    0.75
    IsContent
    0.71
    IContainer
    0.70
    Act Density 0.641%

    No Known Activations