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

    Neuronpedia

    INDEX
    Explanations

    the followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     چیزی
    0.29
     κάτι
    0.29
     आध्यात्म
    0.28
    σίας
    0.28
    こういう
    0.27
     spasms
    0.27
    艨
    0.27
     SupCt
    0.27
    ántico
    0.27
    犹
    0.27
    POSITIVE LOGITS
     entire
    0.34
     tersebut
    0.34
     aforementioned
    0.31
     betreff
    0.28
     bowels
    0.27
     ormai
    0.26
     $\
    0.26
    ire
    0.26
     referido
    0.26
     respective
    0.25
    Act Density 0.126%

    No Known Activations