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

    Neuronpedia

    INDEX
    Explanations

    differential equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     штаб
    -0.09
     눈
    -0.09
    اعات
    -0.09
     хабар
    -0.08
     terpercaya
    -0.08
     progn
    -0.08
    рас
    -0.08
    см
    -0.08
    握
    -0.08
     лек
    -0.08
    POSITIVE LOGITS
    Btns
    0.09
    抵
    0.08
     বিরুদ্ধে
    0.08
     Works
    0.08
     linn
    0.07
     Renewal
    0.07
     troublesome
    0.07
    Styled
    0.07
     respon
    0.07
    Proble
    0.07
    Act Density 0.006%

    No Known Activations