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

    Neuronpedia

    INDEX
    Explanations

    language and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     старо
    0.45
     refinements
    0.45
     Humidity
    0.43
     UNITS
    0.41
    ipation
    0.39
     Skeleton
    0.39
     رکھتے
    0.38
    र्निंग
    0.38
    hb
    0.38
     conditioners
    0.38
    POSITIVE LOGITS
     defini
    0.56
    uencia
    0.52
     exclus
    0.51
     transforma
    0.51
     mencipt
    0.50
     definição
    0.48
     определение
    0.47
     qi
    0.46
    DEFIN
    0.46
    clientsdetails
    0.46
    Act Density 0.000%

    No Known Activations