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

    Neuronpedia

    INDEX
    Explanations

    grew up in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     대학
    0.81
     Lancet
    0.75
    ái
    0.74
    ائج
    0.73
     Anat
    0.73
     newborn
    0.72
    ší
    0.72
     आंकड़े
    0.71
     enseignants
    0.70
     students
    0.70
    POSITIVE LOGITS
     surrounded
    1.16
     hearing
    0.91
     entendido
    0.90
    yo
    0.85
     Surrounded
    0.83
     fostered
    0.81
     flanked
    0.79
    мимо
    0.78
    知道
    0.78
    可知
    0.76
    Act Density 0.015%

    No Known Activations