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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    1.31
    ’.”
    1.23
    ).”
    1.22
    .'”
    1.19
    </strong>
    1.10
    ].”
    1.10
    .’”
    1.08
     !”
    1.06
    <strong>
    1.04
     ।”
    1.04
    POSITIVE LOGITS
    ```
    3.53
     ```
    2.75
    ``
    2.21
    ｣
    1.90
     ``
    1.55
    `,`
    1.48
    `)
    1.47
    `
    1.42
    `](
    1.40
    </img>
    1.38
    Act Density 0.226%

    No Known Activations