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

    Neuronpedia

    INDEX
    Explanations

    Numbers and dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     britannique
    -0.10
     découvrir
    -0.09
     découverte
    -0.09
     découvert
    -0.09
     anglais
    -0.09
     Engelse
    -0.08
     герман
    -0.08
     japonais
    -0.08
     Gladi
    -0.08
     entdecken
    -0.08
    POSITIVE LOGITS
     Colombian
    0.10
     Colombia
    0.09
     Alejandro
    0.09
     Medell
    0.09
     cilantro
    0.09
     Venezuel
    0.09
     acá
    0.08
     Antio
    0.08
     Bogotá
    0.08
     colomb
    0.08
    Act Density 0.046%

    No Known Activations