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

    Neuronpedia

    INDEX
    Explanations

    simplified chinese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нік
    1.86
     TRANSPORTURI
    1.83
    ক
    1.82
    ა
    1.80
    ק
    1.78
    па
    1.77
    не
    1.76
    ג
    1.76
    зи
    1.74
    ке
    1.73
    POSITIVE LOGITS
    ost
    2.16
    ara
    2.06
    yyyy
    1.95
    ot
    1.91
    od
    1.89
    ra
    1.88
    ere
    1.84
    yy
    1.68
    kannya
    1.65
    nen
    1.62
    Act Density 0.013%

    No Known Activations