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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses and curly braces in code

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

    code block delimiters '{' and '}'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )))),
    -0.59
    ))).
    -0.47
    )))));
    -0.45
    XmlRootElement
    -0.41
    )))))
    -0.40
    ))^
    -0.40
     dentelle
    -0.39
    ))),
    -0.39
    :][
    -0.39
     MQTT
    -0.38
    POSITIVE LOGITS
     nahilalakip
    0.72
     AssemblyCulture
    0.67
    BeginContext
    0.59
     Infórmanos
    0.59
    GraphicsUnit
    0.57
     numerus
    0.57
     Administrativna
    0.54
    ParallelGroup
    0.54
    BufferException
    0.54
     propOrder
    0.53
    Act Density 0.006%

    No Known Activations