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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "scope" in code-related contexts

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

    scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.32
    Class
    -0.28
    class
    -0.27
    ksesta
    -0.26
    Allora
    -0.26
    ↵↵
    -0.26
    <eos>
    -0.24
    aderas
    -0.24
     ocurrido
    -0.24
    xmlWriter
    -0.23
    POSITIVE LOGITS
     scope
    1.82
     Scope
    1.57
     scopes
    1.40
    Scope
    1.39
     SCOPE
    1.34
    SCOPE
    1.21
    scope
    1.15
    脚注の使い方
    1.13
     scoped
    1.09
     scoping
    1.02
    Act Density 0.001%

    No Known Activations