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

    Neuronpedia

    INDEX
    Explanations

    imaginary and real numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ल्य
    -0.08
     værd
    -0.08
    jali
    -0.08
    endar
    -0.07
     خاصة
    -0.07
     erity
    -0.07
     waard
    -0.07
     đặc
    -0.07
    aits
    -0.07
    าที่
    -0.07
    POSITIVE LOGITS
     vanish
    0.09
     Küchen
    0.08
     제거
    0.08
    unless
    0.08
     unnecessary
    0.08
     лиш
    0.08
    环球
    0.08
     רוב
    0.08
     রাত
    0.07
    겁
    0.07
    Act Density 0.012%

    No Known Activations