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

    Neuronpedia

    INDEX
    Explanations

    underscore characters, which often signify variable names or specific attributes in programming contexts

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

    header structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.48
    testify
    -0.42
    Javadoc
    -0.42
     ویکی‌پدی
    -0.40
    DebuggerStep
    -0.40
    LookAnd
    -0.40
     personlig
    -0.39
    onAttach
    -0.39
     AppCompatTheme
    -0.38
     igjen
    -0.38
    POSITIVE LOGITS
     index
    0.56
     golos
    0.50
     metadata
    0.48
     keys
    0.48
     key
    0.45
     dimensionality
    0.45
     STORAGE
    0.44
     Schlüssel
    0.44
     Chest
    0.44
     indexes
    0.44
    Act Density 0.002%

    No Known Activations