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

    Neuronpedia

    INDEX
    Explanations

    break

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    赔付
    -0.08
     sir
    -0.07
     Treatment
    -0.07
     Woman
    -0.06
    _FLAG
    -0.06
     ther
    -0.06
     Yi
    -0.06
    辐
    -0.06
    上映
    -0.06
     Weg
    -0.06
    POSITIVE LOGITS
    imagem
    0.07
    ){
    0.07
    (coordinates
    0.07
    ѽ
    0.06
     automate
    0.06
    #import
    0.06
    membership
    0.06
    carousel
    0.06
    _blue
    0.06
    렜
    0.06
    Act Density 0.007%

    No Known Activations