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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     er
    -0.06
    (mem
    -0.06
    agy
    -0.06
    @qq
    -0.06
    raction
    -0.06
    RD
    -0.06
     раз
    -0.06
     cooked
    -0.06
     Esp
    -0.06
     Read
    -0.06
    POSITIVE LOGITS
    vehicles
    0.07
     빌
    0.06
    (""));↵
    0.06
    驶
    0.06
     Yard
    0.06
    سك
    0.06
    TreeWidgetItem
    0.06
     objekt
    0.06
     sling
    0.06
    lesc
    0.06
    Act Density 0.120%

    No Known Activations