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

    Neuronpedia

    INDEX
    Explanations

    comparisons with vs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ataupun
    0.42
     wygląda
    0.36
    <unused635>
    0.35
     Bă
    0.35
     अथवा
    0.34
     Pér
    0.34
     totiž
    0.33
    <unused487>
    0.33
     gdyż
    0.33
     Schiller
    0.33
    POSITIVE LOGITS
    .,
    1.47
    .),
    1.03
    ./
    1.02
    .,"
    1.01
    .;
    0.99
    .:
    0.93
    .).
    0.91
    .):
    0.89
    .)
    0.88
    .);
    0.87
    Act Density 0.141%

    No Known Activations