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

    Neuronpedia

    INDEX
    Explanations

    design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corpore
    -0.08
    哲
    -0.08
     Claudia
    -0.07
    源县
    -0.07
    uisse
    -0.07
    غر
    -0.07
     جنس
    -0.07
     philosophies
    -0.07
    观
    -0.07
     poésie
    -0.07
    POSITIVE LOGITS
     الملفات
    0.08
     Anytime
    0.08
     Кон
    0.08
     user's
    0.08
     يقدم
    0.08
     навед
    0.08
     shak
    0.08
     uploads
    0.07
     любого
    0.07
     versões
    0.07
    Act Density 0.004%

    No Known Activations