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

    Neuronpedia

    INDEX
    Explanations

    Summarizing differences in tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esehen
    0.60
    ﻩ
    0.57
    є
    0.52
     वास
    0.50
     nin
    0.49
    }-[
    0.49
    ocalypse
    0.48
    }^{*}
    0.47
     seeing
    0.47
     }()
    0.47
    POSITIVE LOGITS
    <tr>
    0.74
    |
    0.72
    |-
    0.66
    hline
    0.64
    |$
    0.64
     |-
    0.62
    </tbody>
    0.62
    |=
    0.61
    |,
    0.61
    </thead>
    0.60
    Act Density 0.017%

    No Known Activations