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

    Neuronpedia

    INDEX
    Explanations

    countries and republics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     产品
    0.57
    细菌
    0.57
    针对
    0.53
     ዘዴ
    0.52
     thérapeutique
    0.52
     Calyce
    0.51
    Acetoxy
    0.51
    LastGen
    0.49
    烜
    0.49
     matériau
    0.48
    POSITIVE LOGITS
     countries
    0.88
     país
    0.87
    countries
    0.85
     republics
    0.83
     country
    0.82
     países
    0.82
     Republic
    0.82
    country
    0.81
     negara
    0.77
     republic
    0.77
    Act Density 0.273%

    No Known Activations