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

    Neuronpedia

    INDEX
    Explanations

    hardware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sushi
    -0.07
    租
    -0.07
    นน
    -0.07
     pars
    -0.07
    idian
    -0.07
     آس
    -0.06
     comunic
    -0.06
    较
    -0.06
     danmark
    -0.06
     完
    -0.06
    POSITIVE LOGITS
    .ACT
    0.07
    regex
    0.06
     호텔
    0.06
    Methods
    0.06
    Title
    0.06
    throws
    0.06
     Проф
    0.06
    Combat
    0.06
     CRC
    0.06
     tématu
    0.06
    Act Density 0.063%

    No Known Activations