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

    Neuronpedia

    INDEX
    Explanations

    animal research models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     typography
    -0.09
    bund
    -0.09
     gramm
    -0.08
    Beam
    -0.08
     boosters
    -0.08
     bund
    -0.08
     dips
    -0.08
     antennas
    -0.08
    Listings
    -0.08
    Listing
    -0.08
    POSITIVE LOGITS
     rodents
    0.11
     rabbits
    0.11
     invaluable
    0.11
     animal
    0.10
     animals
    0.10
     животных
    0.10
    牲
    0.10
    动物
    0.10
     surrogate
    0.10
     Animal
    0.10
    Act Density 0.017%

    No Known Activations