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

    Neuronpedia

    INDEX
    Explanations

    code snippets that involve data structure manipulation or element accessing using specific syntax

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

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.96
    AddTagHelper
    -0.93
    saraba
    -0.74
    messageInfo
    -0.73
     Administrativna
    -0.71
     queſta
    -0.68
    AccessorTable
    -0.68
    CloseOperation
    -0.68
    fjspx
    -0.67
    PropertyChanging
    -0.66
    POSITIVE LOGITS
    mod
    0.35
    arch
    0.34
     hyö
    0.33
    THROW
    0.33
     Nieder
    0.33
    fed
    0.32
     käyt
    0.32
     funcionales
    0.32
     Weg
    0.31
     Fahr
    0.31
    Act Density 0.007%

    No Known Activations