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

    Neuronpedia

    INDEX
    Explanations

    opening and closing parentheses in code or data structures

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

    closing parenthesis or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.85
     الحره
    -0.80
     queſta
    -0.73
    Personendaten
    -0.73
     zuſammen
    -0.72
    ftagPool
    -0.71
    Tikang
    -0.66
    parsedMessage
    -0.65
     Normdatei
    -0.65
    ArgumentParser
    -0.65
    POSITIVE LOGITS
    ))))
    0.43
    )))),
    0.39
    ..
    0.38
    ↵
    0.36
    )))))
    0.36
    ))+
    0.35
    …
    0.35
    ))
    0.34
      
    0.34
    ))(
    0.34
    Act Density 0.023%

    No Known Activations