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

    Neuronpedia

    INDEX
    Explanations

    symbolic expressions, specifically parentheses and tags used in programming or documentation

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

    closing punctuation then declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -1.00
    featureID
    -0.95
    Portale
    -0.94
    DotNetBar
    -0.93
    ValueStyle
    -0.92
    ########.
    -0.92
     AssemblyCompany
    -0.91
     Administrativna
    -0.90
    <unused41>
    -0.89
    <unused14>
    -0.88
    POSITIVE LOGITS
    )
    0.78
    ))
    0.73
    '))
    0.69
    ']))
    0.69
    ')
    0.69
    }])
    0.69
     )
    0.67
    ]))
    0.67
    ])
    0.66
    )))
    0.65
    Act Density 0.012%

    No Known Activations