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

    Neuronpedia

    INDEX
    Explanations

    bouncing/reflection code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     που
    -0.08
    柏
    -0.08
    াধ
    -0.08
     cheminée
    -0.07
     Copenhagen
    -0.07
     respeito
    -0.07
     cómoda
    -0.07
     compreh
    -0.07
     emp
    -0.07
     શું
    -0.07
    POSITIVE LOGITS
     entradas
    0.07
     Injector
    0.07
     مستويات
    0.07
    (private
    0.07
    experienced
    0.07
     waka
    0.07
     experienced
    0.07
    XP
    0.07
     interpolate
    0.07
    inks
    0.07
    Act Density 0.005%

    No Known Activations