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

    Neuronpedia

    INDEX
    Explanations

    punctuations, specifically parentheses and brackets, indicating structured data or code

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

    Closing parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses, brackets, and braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NDEBUG
    -0.86
     itſelf
    -0.84
    StoryboardSegue
    -0.83
    stdc
    -0.83
    رشف
    -0.80
    IntoConstraints
    -0.74
    ︎
    -0.72
    moreland
    -0.71
     myſelf
    -0.70
     Ibid
    -0.70
    POSITIVE LOGITS
    )))
    0.80
    ())))
    0.77
    )))
    0.75
    ']))
    0.74
    ()))
    0.74
    ))
    0.73
    "]))
    0.73
     ?>">
    0.73
    ]}>
    0.72
    ")))
    0.71
    Act Density 0.718%

    No Known Activations