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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faça
    -0.08
     arr
    -0.08
     činjen
    -0.07
     forne
    -0.07
    outes
    -0.07
    ativamente
    -0.07
     Tutors
    -0.07
    യായി
    -0.07
     buka
    -0.07
     execut
    -0.07
    POSITIVE LOGITS
     earlier
    0.10
     tẹlẹ
    0.10
     discussed
    0.09
    Earlier
    0.09
     previously
    0.08
     Elijah
    0.08
    ._
    0.08
     ранее
    0.08
     elsewhere
    0.08
    上一篇
    0.08
    Act Density 0.100%

    No Known Activations