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

    Neuronpedia

    INDEX
    Explanations

    numerical ages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     little
    0.78
    Little
    0.75
     wiggle
    0.75
     toys
    0.70
     малы
    0.69
     arası
    0.69
     সকাল
    0.69
     preschoolers
    0.68
     babies
    0.67
     toy
    0.66
    POSITIVE LOGITS
     twenties
    1.04
     thirties
    1.03
    thirty
    0.98
     thirty
    0.96
    fifty
    0.94
    retired
    0.91
     Thirty
    0.90
    Thirty
    0.88
    twenty
    0.87
     forty
    0.86
    Act Density 0.088%

    No Known Activations