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

    Neuronpedia

    INDEX
    Explanations

    ethics and standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    할
    -0.07
    夫
    -0.06
    (GPIO
    -0.06
     dominated
    -0.06
     afl
    -0.06
     persist
    -0.06
    Aws
    -0.06
    NGTH
    -0.06
     orchestra
    -0.06
    리를
    -0.06
    POSITIVE LOGITS
     spis
    0.07
     �
    0.07
     sos
    0.07
    (module
    0.06
     proliferation
    0.06
    uploads
    0.06
    serializer
    0.06
     PropertyInfo
    0.06
     выгляд
    0.06
     Kah
    0.06
    Act Density 0.015%

    No Known Activations