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

    Neuronpedia

    INDEX
    Explanations

    Keras neural network layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Checksum
    -0.09
     نقل
    -0.08
    客户端
    -0.08
    Client
    -0.08
    _checksum
    -0.07
     целью
    -0.07
    جه
    -0.07
    _client
    -0.07
    笑
    -0.07
     oficialmente
    -0.07
    POSITIVE LOGITS
     Sized
    0.10
     sized
    0.10
    -size
    0.09
     Jardim
    0.09
    -sized
    0.09
     bloom
    0.09
    Sized
    0.08
     Mor
    0.08
     parques
    0.08
     burge
    0.08
    Act Density 0.003%

    No Known Activations