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

    Neuronpedia

    INDEX
    Explanations

    Thank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     controvers
    -0.07
    ころ
    -0.07
    Deserializer
    -0.07
    аг
    -0.06
    rovers
    -0.06
     ARCH
    -0.06
     العرب
    -0.06
     maize
    -0.06
    ()`
    -0.06
     counts
    -0.06
    POSITIVE LOGITS
     enthus
    0.07
     Ethnic
    0.06
    _flutter
    0.06
    Xd
    0.06
    \Domain
    0.06
     Turkish
    0.06
     storage
    0.06
     rdf
    0.06
     crash
    0.06
     endregion
    0.06
    Act Density 0.006%

    No Known Activations