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

    Neuronpedia

    INDEX
    Explanations

    oxide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hospitality
    -0.09
    782
    -0.08
     envy
    -0.08
     bien
    -0.08
     자리
    -0.08
     �
    -0.08
     cryst
    -0.08
     ketosis
    -0.08
     lotteries
    -0.08
     jewelry
    -0.08
    POSITIVE LOGITS
    -producing
    0.08
    produ
    0.08
     produtor
    0.07
    production
    0.07
     উৎপ
    0.07
    produktion
    0.07
    aron
    0.07
     originating
    0.07
     epsilon
    0.07
     সৃষ্টি
    0.07
    Act Density 0.001%

    No Known Activations