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
     Tas
    -0.08
    给宝宝
    -0.08
    带给
    -0.08
    受访者
    -0.08
    alk
    -0.07
     الأسهم
    -0.07
    写了
    -0.07
    tracer
    -0.07
    榇
    -0.07
    白领
    -0.07
    POSITIVE LOGITS
    forget
    0.07
    ,status
    0.07
     pl
    0.07
     Geschä
    0.07
    */↵↵↵
    0.07
    elijk
    0.06
    どういう
    0.06
    ủng
    0.06
    ">
↵
    0.06
     loại
    0.06
    Act Density 0.025%

    No Known Activations