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

    Neuronpedia

    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foremost
    -0.06
    herent
    -0.06
    يمة
    -0.06
    	f
    -0.06
     مکان
    -0.06
     startling
    -0.06
     Conservatives
    -0.06
     sweaty
    -0.06
    .parameter
    -0.06
    	top
    -0.06
    POSITIVE LOGITS
    ！！
    0.06
    indows
    0.06
    .setter
    0.06
    降
    0.06
    (Node
    0.06
     GHz
    0.06
    llib
    0.06
     compare
    0.06
    ——
    0.06
     buys
    0.06
    Act Density 0.015%

    No Known Activations