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

    Neuronpedia

    INDEX
    Explanations

    nationalities and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evaporation
    0.65
     changes
    0.64
     sanding
    0.63
     any
    0.62
     flimsy
    0.62
     vacuoles
    0.61
     units
    0.61
     mirrored
    0.60
     slats
    0.60
     evaporates
    0.60
    POSITIVE LOGITS
    businessman
    0.90
     businessman
    0.88
     ehemalige
    0.85
     seorang
    0.84
     biographer
    0.83
     ehemal
    0.80
     Schriftsteller
    0.80
     physician
    0.79
    uomo
    0.79
     Physician
    0.79
    Act Density 0.018%

    No Known Activations