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

    Neuronpedia

    INDEX
    Explanations

    book titles and subtitles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Villas
    0.30
     Scott
    0.30
     Rihanna
    0.30
     James
    0.28
     Bak
    0.27
     Hughes
    0.27
     Blau
    0.27
    <strong>
    0.27
     Ryan
    0.27
     Williams
    0.27
    POSITIVE LOGITS
    <unused1092>
    0.52
    <unused549>
    0.49
    <unused277>
    0.49
    <unused997>
    0.49
    <unused1089>
    0.49
    <unused428>
    0.49
    <unused525>
    0.48
    <unused646>
    0.48
    <unused432>
    0.48
    <unused729>
    0.48
    Act Density 0.000%

    No Known Activations