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

    Neuronpedia

    INDEX
    Explanations

    marginalized groups and populations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uomini
    0.74
     monde
    0.71
     hombres
    0.71
     sincron
    0.68
     attitudes
    0.68
     linear
    0.68
     Wilde
    0.64
     synchron
    0.64
    ➚
    0.63
    hype
    0.63
    POSITIVE LOGITS
     minorities
    1.05
     minority
    1.05
     vulnerable
    0.97
     Minority
    0.93
     Vulner
    0.90
    ulnerable
    0.88
     marginalized
    0.88
     disadvantaged
    0.87
    弱
    0.87
     marginalised
    0.86
    Act Density 0.233%

    No Known Activations