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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CIS
    -0.07
    Sol
    -0.07
    植
    -0.06
    ственные
    -0.06
    Він
    -0.06
     pedestal
    -0.06
    "Do
    -0.06
    微软雅黑
    -0.06
     Sử
    -0.06
    ۲۳
    -0.06
    POSITIVE LOGITS
     prow
    0.07
    _po
    0.07
    _EPS
    0.07
    ving
    0.07
     (--
    0.06
    (entities
    0.06
    -art
    0.06
    _pix
    0.06
    向
    0.06
     --
    0.06
    Act Density 0.008%

    No Known Activations