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

    Neuronpedia

    INDEX
    Explanations

    ReLU

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ­t
    -0.07
    -V
    -0.07
     �
    -0.07
     �
    -0.06
    extern
    -0.06
    ­n
    -0.06
     vig
    -0.06
    .temperature
    -0.06
     bytecode
    -0.06
     incapac
    -0.06
    POSITIVE LOGITS
    Updating
    0.07
    .branch
    0.07
    tls
    0.06
    _vendor
    0.06
     Spy
    0.06
    patibility
    0.06
    DataService
    0.06
    cdf
    0.06
    Spy
    0.06
    TypeId
    0.06
    Act Density 0.005%

    No Known Activations