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

    Neuronpedia

    INDEX
    Explanations

    numbers, punctuation, and special characters within or next to words.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    th
    -0.82
    nd
    -0.75
    rd
    -0.72
    st
    -0.69
    ArgsConstructor
    -0.64
    bootstrapcdn
    -0.62
    ″
    -0.62
    월
    -0.56
     defaultstate
    -0.56
    个
    -0.54
    POSITIVE LOGITS
    ſelf
    0.60
    utives
    0.59
    orna
    0.57
    SharedDtor
    0.57
    MessageTagHelper
    0.57
    UMENTS
    0.56
     lenker
    0.56
    inerary
    0.56
    xiety
    0.56
     Савезне
    0.55
    Act Density 14.500%

    No Known Activations