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

    Neuronpedia

    INDEX
    Explanations

    authorization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中医药
    -0.07
    Toolkit
    -0.07
     sider
    -0.07
    SOEVER
    -0.07
    ฬ
    -0.07
    vier
    -0.06
    芸
    -0.06
     mgr
    -0.06
    .Dis
    -0.06
    -scrollbar
    -0.06
    POSITIVE LOGITS
    Weights
    0.08
    :length
    0.07
    anca
    0.06
     strap
    0.06
    .products
    0.06
     sweat
    0.06
     trespass
    0.06
    :view
    0.06
    orque
    0.06
     Virgin
    0.06
    Act Density 0.013%

    No Known Activations