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

    Neuronpedia

    INDEX
    Explanations

    book reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Nazi
    -0.06
    semi
    -0.06
     slices
    -0.06
     fractures
    -0.06
     Mountains
    -0.06
     whales
    -0.06
     середови
    -0.06
     psychiatrist
    -0.05
    .labels
    -0.05
     ниже
    -0.05
    POSITIVE LOGITS
    驚
    0.07
     lệ
    0.07
    ích
    0.07
    珠
    0.07
    ymph
    0.06
    ież
    0.06
    twig
    0.06
    ziel
    0.06
     Steve
    0.06
    وق
    0.06
    Act Density 0.037%

    No Known Activations