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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and structure

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

    code constructs and templating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.59
    rlpool
    -0.57
     ſind
    -0.57
    MemoryWarning
    -0.53
    styleType
    -0.52
     imagui
    -0.52
    <unused47>
    -0.51
     Dieſe
    -0.51
    <unused7>
    -0.51
    <unused80>
    -0.50
    POSITIVE LOGITS
    ViewFeatures
    0.46
    Rüyada
    0.44
    SourceChecksum
    0.42
    High
    0.39
    readFileSync
    0.38
     products
    0.36
    generate
    0.36
     High
    0.36
    StringBuilder
    0.36
     seq
    0.36
    Act Density 0.192%

    No Known Activations