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

    Neuronpedia

    INDEX
    Explanations

    birth and babies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     degr
    0.78
     выполнить
    0.77
     podnik
    0.76
     टिकट
    0.76
     작업을
    0.75
     Corrosion
    0.73
     작업
    0.72
     rivet
    0.72
    operand
    0.72
    Cyber
    0.72
    POSITIVE LOGITS
     baby
    3.41
     babies
    3.26
     newborn
    3.08
     newborns
    3.01
     Baby
    3.00
    Baby
    2.86
     infant
    2.86
     Babies
    2.84
    baby
    2.84
     infants
    2.76
    Act Density 0.310%

    No Known Activations