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

    Neuronpedia

    INDEX
    Explanations

    Family and community roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     billions
    0.50
    ில்லியன்
    0.50
    erver
    0.48
    utsche
    0.48
    innitus
    0.48
     trillions
    0.47
    etop
    0.47
     miliardi
    0.47
    大脑
    0.47
    restrial
    0.47
    POSITIVE LOGITS
     Women
    0.54
     women
    0.51
     femminile
    0.48
     Family
    0.47
     وض
    0.46
     Rural
    0.45
    婦
    0.45
     Education
    0.45
     mujeres
    0.45
     School
    0.45
    Act Density 0.007%

    No Known Activations