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

    Neuronpedia

    INDEX
    Explanations

    78

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     форме
    -0.06
    etal
    -0.06
    link
    -0.06
    IsRequired
    -0.06
    cio
    -0.06
    elu
    -0.06
    lendirme
    -0.06
    aut
    -0.06
     Yönetim
    -0.06
    Cfg
    -0.05
    POSITIVE LOGITS
     учрежд
    0.07
    一级
    0.07
    dock
    0.07
     toàn
    0.07
    rowing
    0.07
     antenn
    0.06
    Visualization
    0.06
     impover
    0.06
               ↵
    0.06
     Paid
    0.06
    Act Density 0.540%

    No Known Activations