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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     알고
    -0.06
    맛
    -0.06
    -В
    -0.06
    HV
    -0.06
     полі
    -0.06
     An
    -0.06
    Mapper
    -0.06
     rè
    -0.06
     tự
    -0.06
     spanking
    -0.06
    POSITIVE LOGITS
     fotos
    0.06
    éric
    0.06
    iams
    0.06
    Bezier
    0.06
     Vault
    0.06
    орт
    0.06
    $(
    0.06
    retim
    0.06
    уст
    0.06
    means
    0.06
    Act Density 0.061%

    No Known Activations