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

    Neuronpedia

    INDEX
    Explanations

    synthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Paul
    -0.07
     Paul
    -0.06
    Shop
    -0.06
     Cultural
    -0.06
     fran
    -0.06
    ��
    -0.06
     Duc
    -0.06
    olit
    -0.06
     Republican
    -0.06
    Nodes
    -0.06
    POSITIVE LOGITS
    皆
    0.06
    ЛИ
    0.06
    зем
    0.06
     tls
    0.06
    .DB
    0.06
    /cms
    0.06
     conson
    0.06
    بس
    0.06
    plane
    0.06
    ABS
    0.06
    Act Density 0.019%

    No Known Activations