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

    Neuronpedia

    INDEX
    Explanations

    village names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Recruitment
    -0.77
    ngiliz
    -0.75
    ñora
    -0.73
    barn
    -0.70
     bleek
    -0.68
     поту
    -0.67
    💥
    -0.66
    lottesville
    -0.66
     Zier
    -0.65
     Tasse
    -0.65
    POSITIVE LOGITS
     village
    1.24
     Sm
    1.18
     Garg
    1.14
     Pey
    1.02
     villages
    0.97
     Village
    0.96
    village
    0.91
    Sm
    0.89
    Village
    0.88
     Handy
    0.88
    Act Density 0.012%

    No Known Activations