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

    Neuronpedia

    INDEX
    Explanations

    code formatting and structurecode syntax elementsprogramming code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KINS
    0.45
     hydraz
    0.44
     hepat
    0.43
     carbox
    0.43
     reduzir
    0.43
    ہوں
    0.42
     crisi
    0.42
    ەم
    0.42
     ryzy
    0.42
    من
    0.42
    POSITIVE LOGITS
    </table>
    0.49
    分隔
    0.48
     Далее
    0.48
    newline
    0.47
    smallskip
    0.46
    <tr>
    0.46
    vspace
    0.45
     Kemudian
    0.45
    style
    0.44
     Затем
    0.44
    Act Density 0.126%

    No Known Activations