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
    长效
    -0.07
    odule
    -0.07
    支架
    -0.07
    /ic
    -0.07
    جريمة
    -0.07
    叶片
    -0.07
    rist
    -0.07
    侣
    -0.07
    _REQUIRE
    -0.07
     volunteer
    -0.07
    POSITIVE LOGITS
    �
    0.07
     Mundo
    0.07
     rağ
    0.06
     requ
    0.06
     incidence
    0.06
     atrav
    0.06
     repr
    0.06
    咴
    0.06
    cona
    0.06
    traî
    0.06
    Act Density 0.009%

    No Known Activations