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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manna
    -0.09
     राष्ट्र
    -0.08
     pinta
    -0.08
     prosec
    -0.08
    -made
    -0.07
     उद्घ
    -0.07
    ŋ
    -0.07
     inventions
    -0.07
     allergic
    -0.07
    meni
    -0.07
    POSITIVE LOGITS
    Wikipedia
    0.09
    平台
    0.09
    Netflix
    0.09
     Wikimedia
    0.08
     Netflix
    0.08
    法院
    0.08
     plataformas
    0.08
     сайте
    0.08
     platforms
    0.08
    沙
    0.08
    Act Density 0.063%

    No Known Activations