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

    Neuronpedia

    INDEX
    Explanations

    app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gren
    -0.07
    {}_
    -0.07
     Mouth
    -0.07
    سنگ
    -0.07
    fav
    -0.07
     YORK
    -0.06
    在线观看
    -0.06
    ahrung
    -0.06
    stock
    -0.06
     cured
    -0.06
    POSITIVE LOGITS
     इस
    0.06
     deficit
    0.06
     نیاز
    0.06
     udp
    0.06
     objedn
    0.06
     liquid
    0.05
     přest
    0.05
    _decision
    0.05
     cev
    0.05
    ắp
    0.05
    Act Density 0.004%

    No Known Activations