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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vital
    -0.07
    naires
    -0.07
    Vertices
    -0.07
    smart
    -0.07
    billing
    -0.06
     Barker
    -0.06
    materials
    -0.06
    layers
    -0.06
    خی
    -0.06
    rait
    -0.06
    POSITIVE LOGITS
     reife
    0.06
    ượ
    0.06
    도가
    0.06
    .PropTypes
    0.06
     يق
    0.06
    牛
    0.06
    cono
    0.06
     Bonds
    0.06
    .shop
    0.06
     closeButton
    0.06
    Act Density 0.019%

    No Known Activations