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

    Neuronpedia

    INDEX
    Explanations

    curly braces and parentheses in a mathematical or programming context

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

    code-like structures with brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.68
     enfans
    -0.67
    XmlAccessorType
    -0.67
     kapture
    -0.61
     indígen
    -0.59
    MessageOf
    -0.59
     AssemblyTitle
    -0.57
     voordelen
    -0.57
     mijne
    -0.57
    httphttps
    -0.56
    POSITIVE LOGITS
    LikeLike
    0.49
    LikeLiked
    0.41
     Senhora
    0.40
    RSpec
    0.40
    YMMV
    0.39
    🟩
    0.39
    ":"",
    0.38
     [];
    0.38
    ({});
    0.37
     blank
    0.35
    Act Density 0.070%

    No Known Activations