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

    Neuronpedia

    INDEX
    Explanations

    talking about people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tends
    1.26
     has
    1.19
     allows
    1.17
     affords
    1.12
     seems
    1.11
     gives
    1.08
     simplifies
    1.07
     deserves
    1.04
     speeds
    1.03
    ซ์
    1.03
    POSITIVE LOGITS
     którzy
    1.52
     quienes
    1.49
     miembros
    1.46
     ktorí
    1.46
     kteří
    1.45
     женщин
    1.44
     pracowników
    1.41
     лиц
    1.38
     мужчин
    1.37
     людей
    1.36
    Act Density 0.852%

    No Known Activations