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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ivory
    -0.07
    getCode
    -0.07
    yl
    -0.07
    AREN
    -0.07
     turning
    -0.06
    placed
    -0.06
    쥐
    -0.06
    มาณ
    -0.06
    .events
    -0.06
     altru
    -0.06
    POSITIVE LOGITS
    户外
    0.07
    精选
    0.07
    爸妈
    0.07
    峰
    0.06
    讲
    0.06
     woman
    0.06
    Supported
    0.06
    ;
↵
↵
    0.06
    部落
    0.06
    Ads
    0.06
    Act Density 0.015%

    No Known Activations