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

    Neuronpedia

    INDEX
    Explanations

    Code/diagram snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oods
    -0.09
     தெர
    -0.08
     kilogram
    -0.07
     Tyler
    -0.07
     agency
    -0.07
     clinic
    -0.07
    PILE
    -0.07
    ylie
    -0.07
     τύ
    -0.07
     ziekenhuis
    -0.07
    POSITIVE LOGITS
     hacía
    0.08
    ಾವ
    0.08
    duino
    0.08
     Blanca
    0.08
     никак
    0.08
     trajetória
    0.08
     ineff
    0.08
     Backbone
    0.08
    ર્ક
    0.08
    merksam
    0.07
    Act Density 0.003%

    No Known Activations