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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    阿根廷
    -0.07
     만
    -0.07
    różni
    -0.07
    ocrat
    -0.07
     JsonRequestBehavior
    -0.06
    rippling
    -0.06
     reconnaissance
    -0.06
     יורק
    -0.06
     arbitrary
    -0.06
     addresses
    -0.06
    POSITIVE LOGITS
    Play
    0.08
    虚拟
    0.08
    gift
    0.07
    -family
    0.07
    media
    0.07
    _FORM
    0.07
    ий
    0.07
    線上
    0.06
    商業
    0.06
    -te
    0.06
    Act Density 0.064%

    No Known Activations