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

    Neuronpedia

    INDEX
    Explanations

    parentheses and related syntax in code snippets

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

    closing parentheses and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused52>
    -1.38
    <unused41>
    -1.38
    <unused28>
    -1.38
    [@BOS@]
    -1.38
    <unused23>
    -1.38
    <unused14>
    -1.38
    <unused17>
    -1.38
    <unused16>
    -1.38
    <unused3>
    -1.38
    <unused8>
    -1.38
    POSITIVE LOGITS
    )
    0.82
    ))
    0.77
    ])
    0.74
     )
    0.70
    })
    0.70
    ()
    0.64
    )))
    0.61
    .
    0.61
    ')
    0.60
    ())
    0.60
    Act Density 0.077%

    No Known Activations