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

    Neuronpedia

    INDEX
    Explanations

    tabular comparisons and summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ceiver
    0.90
     daisies
    0.90
    tał
    0.83
     volat
    0.83
    tać
    0.82
     الي
    0.81
     COLLE
    0.81
     लेणी
    0.81
    痍
    0.80
    辮
    0.79
    POSITIVE LOGITS
    ---|
    1.10
    &
    0.86
    ----------------
    0.86
    ------
    0.81
    ----
    0.77
    <tr>
    0.73
    hline
    0.72
    --------------
    0.69
    ---
    0.69
    -----
    0.69
    Act Density 0.060%

    No Known Activations