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

    Neuronpedia

    INDEX
    Explanations

    C-style multi-line comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kreises
    -2.41
    女
    -2.25
     شیپور
    -2.19
    ～。
    -2.17
    <td>
    -2.14
    蹌
    -2.14
    戬
    -2.11
    擻
    -2.09
    ሯ
    -2.06
    !");
    -2.05
    POSITIVE LOGITS
    re
    3.06
    .
    2.83
    [
    2.72
    ?”
    2.52
    1
    2.48
    as
    2.48
    E
    2.48
    un
    2.44
    (
    2.38
     یه
    2.31
    Act Density 0.002%

    No Known Activations