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

    Neuronpedia

    INDEX
    Explanations

    modular arithmetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jedi
    -0.09
     নেতৃত্ব
    -0.08
    Gest
    -0.08
    印度
    -0.08
     ос
    -0.08
     Gest
    -0.08
    orca
    -0.08
     tango
    -0.08
     বাস্ত
    -0.08
    দেশ
    -0.08
    POSITIVE LOGITS
     따르면
    0.07
    _TR
    0.07
     heen
    0.07
     torr
    0.07
     소
    0.07
    .TR
    0.07
     Blackburn
    0.06
     puisqu
    0.06
    _RD
    0.06
    _IGNORE
    0.06
    Act Density 0.027%

    No Known Activations