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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     illustrate
    -0.07
     meaning
    -0.07
    іти
    -0.06
     arrives
    -0.06
    (command
    -0.06
     LCD
    -0.06
    东西
    -0.06
    يج
    -0.06
     Husband
    -0.06
    приклад
    -0.06
    POSITIVE LOGITS
    金融
    0.07
    abl
    0.07
    -txt
    0.07
     ikt
    0.07
    .getColumnModel
    0.06
     <-
    0.06
    Life
    0.06
     sentir
    0.06
     Shopify
    0.06
     profoundly
    0.06
    Act Density 0.004%

    No Known Activations