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

    Neuronpedia

    INDEX
    Explanations

    Pomerania and Seaborn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dragging
    -0.06
     весь
    -0.06
    thag
    -0.06
     результ
    -0.06
     �
    -0.06
     Batı
    -0.06
     Canberra
    -0.06
     nuestros
    -0.06
    сят
    -0.06
     лю
    -0.06
    POSITIVE LOGITS
     RCC
    0.11
     Costco
    0.08
    itin
    0.08
     ACS
    0.08
    การ
    0.07
    ixo
    0.07
     Junk
    0.07
    성
    0.07
     Sem
    0.06
    лін
    0.06
    Act Density 0.004%

    No Known Activations