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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    标
    -0.08
     emblem
    -0.07
     emm
    -0.07
    834
    -0.07
     ciment
    -0.07
     nat
    -0.07
    งาน
    -0.07
     bonds
    -0.07
     cura
    -0.07
     ಶ
    -0.07
    POSITIVE LOGITS
     प्रतिस
    0.08
     الأول
    0.08
     gerek
    0.08
     nữa
    0.07
     convenient
    0.07
     conveniente
    0.07
    mea
    0.07
     buildup
    0.07
     competitivo
    0.07
     swim
    0.07
    Act Density 0.054%

    No Known Activations