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

    Neuronpedia

    INDEX
    Explanations

    within the United States

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    سون
    0.57
     printing
    0.45
     Printed
    0.45
     PRINT
    0.44
    س
    0.44
    ウン
    0.44
     modem
    0.44
     Raf
    0.43
    ة
    0.43
     Domin
    0.42
    POSITIVE LOGITS
    niem
    0.50
    Medicare
    0.46
    covite
    0.45
    {,}
    0.44
    Gosudarstvennyj
    0.42
     Архивная
    0.40
    $)$.
    0.40
     опытом
    0.40
     Justiça
    0.39
     risked
    0.39
    Act Density 0.002%

    No Known Activations