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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation after indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >.
    0.89
    .\"
    0.75
    \".
    0.71
    ![
    0.70
    |.
    0.70
    ?).
    0.70
    ?",
    0.70
    ='\
    0.69
    '."
    0.68
    ?”.
    0.68
    POSITIVE LOGITS
    )
    1.70
    ]
    1.60
    }
    1.53
    \}
    1.07
    ')
    1.05
    ”
    1.03
    ）
    1.01
    ()
    1.00
    ']
    0.95
    】
    0.91
    Act Density 0.516%

    No Known Activations