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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially quotation marks and commas in various contexts

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

    code with quotes and arrays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )))))
    -0.75
    ])))
    -0.75
    ')))
    -0.71
    )))),
    -0.71
    ]))
    -0.68
    ())))
    -0.68
    })),
    -0.67
    ))))
    -0.66
    ")))
    -0.66
    ])),
    -0.65
    POSITIVE LOGITS
     հղումներ
    0.81
    Datuak
    0.81
    ftagPool
    0.81
     كومونز
    0.76
     snippetHide
    0.76
    Зноскі
    0.75
     المعيارى
    0.74
    principalColumn
    0.74
     الحره
    0.73
    InjectAttribute
    0.72
    Act Density 0.053%

    No Known Activations