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

    Neuronpedia

    INDEX
    Explanations

    numerical or titled lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অধীন
    0.41
    ங்கிய
    0.40
     проходит
    0.39
    another
    0.38
    <0xE3>
    0.37
     대해
    0.37
    ANGMAR
    0.37
     snaps
    0.37
    章
    0.37
    城
    0.37
    POSITIVE LOGITS
     Almanac
    0.45
     indispens
    0.43
    感动
    0.41
     mejores
    0.40
    匮
    0.40
     बिलकुल
    0.38
     Annot
    0.38
    を活用
    0.38
     prophecies
    0.38
     Annotated
    0.38
    Act Density 0.001%

    No Known Activations