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

    Neuronpedia

    INDEX
    Explanations

    click

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thinks
    -0.08
    (Direction
    -0.06
     sits
    -0.06
    blocks
    -0.06
     dört
    -0.06
     lur
    -0.06
     Pale
    -0.06
    sender
    -0.06
     actual
    -0.06
     سری
    -0.06
    POSITIVE LOGITS
    Зап
    0.07
     мик
    0.06
    /svg
    0.06
    myfile
    0.06
    [](
    0.06
     řešení
    0.06
    оград
    0.06
     mined
    0.06
     диаг
    0.06
    England
    0.06
    Act Density 0.025%

    No Known Activations