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

    Neuronpedia

    INDEX
    Explanations

    graph data points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     irritation
    -0.08
    \Order
    -0.08
     draagt
    -0.08
    celand
    -0.08
     irrit
    -0.07
     irritating
    -0.07
     Oku
    -0.07
    SQLException
    -0.07
    あなた
    -0.07
     clarification
    -0.07
    POSITIVE LOGITS
     plotted
    0.09
     гу
    0.08
     taller
    0.08
    /value
    0.08
    .ylabel
    0.08
     yax
    0.08
     mús
    0.08
     النق
    0.08
    ليل
    0.08
    .ax
    0.07
    Act Density 0.015%

    No Known Activations