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

    Neuronpedia

    INDEX
    Explanations

    countries and populations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kembali
    0.65
    ペ
    0.63
     aku
    0.63
     Kembali
    0.61
     yang
    0.60
    aktif
    0.60
     akan
    0.60
    को
    0.60
     baru
    0.60
    ケン
    0.60
    POSITIVE LOGITS
     população
    0.76
     comunità
    0.76
     idios
    0.72
     comunidade
    0.71
     popolo
    0.70
     মানুষের
    0.68
     정부
    0.67
     metodologia
    0.66
     mieszkań
    0.65
     population
    0.65
    Act Density 0.000%

    No Known Activations