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

    Neuronpedia

    INDEX
    Explanations

    code structures and keywords in programming languages, particularly related to class definitions and method declarations

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

    Code-related terms following colons or angle brackets

    np_acts-logits-general · gemini-2.0-flash

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TokenType
    -0.48
    '
    -0.44
     ProductService
    -0.44
     UserRepository
    -0.44
     UserService
    -0.42
     since
    -0.42
     OkHttpClient
    -0.41
    ‌آ
    -0.41
    PointSize
    -0.40
    .
    -0.40
    POSITIVE LOGITS
     ModelExpression
    1.05
    Personendaten
    1.03
     للمعارف
    1.03
     متعلقه
    1.01
     Normdatei
    0.98
     Chwiliwch
    0.97
    }-*/;
    0.95
    Datuak
    0.94
    AddTagHelper
    0.94
    rungsseite
    0.90
    Act Density 0.181%

    No Known Activations