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

    Neuronpedia

    INDEX
    Explanations

    Programming text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ONE
    -0.07
     Мари
    -0.06
     програм
    -0.06
    /host
    -0.06
     cons
    -0.06
    цеп
    -0.06
     much
    -0.06
    much
    -0.06
    .Cons
    -0.06
    чі
    -0.06
    POSITIVE LOGITS
    actors
    0.06
    .Track
    0.06
    atten
    0.06
    $q
    0.06
    \"></
    0.06
     clk
    0.06
    "/>
↵
    0.06
     haf
    0.06
    ={[↵
    0.06
    rün
    0.06
    Act Density 0.015%

    No Known Activations