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

    Neuronpedia

    INDEX
    Explanations

    carcinogen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (left
    -0.07
    Վ
    -0.06
     Sp
    -0.06
    路桥
    -0.06
     보기
    -0.06
    ступ
    -0.06
    手指
    -0.06
    和平
    -0.06
     horn
    -0.06
    本次交易
    -0.06
    POSITIVE LOGITS
    ReceiveMemoryWarning
    0.07
     questão
    0.07
     lol
    0.07
    مؤسسات
    0.07
    榜
    0.07
    广大市民
    0.07
    -seven
    0.07
     Alerts
    0.07
    .line
    0.07
    (suffix
    0.07
    Act Density 0.005%

    No Known Activations