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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     часу
    -0.07
    화
    -0.07
    (style
    -0.06
     preached
    -0.06
     turnout
    -0.06
    (dest
    -0.06
     crumbs
    -0.06
     ce
    -0.06
     às
    -0.06
     звичай
    -0.06
    POSITIVE LOGITS
    .PNG
    0.07
    .Non
    0.06
    Run
    0.06
    --------------------------------
    0.06
    md
    0.06
    mongo
    0.06
     التر
    0.06
    XI
    0.06
    Ensure
    0.06
    operators
    0.06
    Act Density 0.001%

    No Known Activations