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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns followed by people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विविध
    0.76
     abilities
    0.72
     capabilities
    0.72
     respective
    0.71
     ক্রম
    0.70
     ability
    0.70
     particular
    0.69
     défini
    0.68
     présence
    0.67
     вмі
    0.66
    POSITIVE LOGITS
     tofu
    0.87
     jeans
    0.81
     Lego
    0.81
     grandpa
    0.78
     boyfriend
    0.78
     puppy
    0.78
     beer
    0.77
     pizza
    0.77
     shampoo
    0.77
     tacos
    0.76
    Act Density 0.037%

    No Known Activations