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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax common in programming languages

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

    Code relating to name maps or targets

    np_acts-logits-general · gemini-2.0-flash

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jScrollPane
    -0.80
     autorytatywna
    -0.78
    LabelTagHelper
    -0.69
    IntoConstraints
    -0.66
     ModelExpression
    -0.66
     Affiliations
    -0.65
     setDescription
    -0.65
     surla
    -0.64
    ReusableCell
    -0.62
     ProtoMessage
    -0.62
    POSITIVE LOGITS
     "<
    0.48
     `<
    0.47
     '<
    0.46
    ▼
    0.45
    ("<
    0.44
    ="<
    0.43
     sonda
    0.43
    チャ
    0.42
     SUR
    0.42
    mbrie
    0.41
    Act Density 0.290%

    No Known Activations