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

    Neuronpedia

    INDEX
    Explanations

    specific codes or identifiers, particularly related to medical or scientific terminologies

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

    Appears before bracketed expressions or mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical or code abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )]{
    -0.54
     T
    -0.53
     M
    -0.51
     Par
    -0.50
    complexContent
    -0.49
    -
    -0.49
     nahilalakip
    -0.48
     bei
    -0.48
    RenderAtEndOf
    -0.48
    IUrlHelper
    -0.47
    POSITIVE LOGITS
     myſelf
    1.23
     pleaſure
    1.05
     whoſe
    1.00
     ſtate
    1.00
     reaſon
    0.97
     himſelf
    0.96
     leſs
    0.95
     laſt
    0.94
     ſeveral
    0.94
     perſon
    0.93
    Act Density 0.583%

    No Known Activations