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

    Neuronpedia

    INDEX
    Explanations

    simply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mädchen
    -0.08
     crianças
    -0.08
    起草
    -0.08
     chart
    -0.08
     Neptune
    -0.08
    توفر
    -0.08
     China
    -0.07
     sdk
    -0.07
    解脱
    -0.07
    違って
    -0.07
    POSITIVE LOGITS
    ("="
    0.08
     simply
    0.07
    Simply
    0.07
     Civil
    0.07
     NIL
    0.07
    对我说
    0.07
     Simply
    0.07
    赝
    0.07
     EI
    0.06
    变速
    0.06
    Act Density 0.017%

    No Known Activations