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

    Neuronpedia

    INDEX
    Explanations

    protocol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     age
    -0.09
    erer
    -0.08
    556
    -0.08
     smaller
    -0.08
     ز
    -0.08
     number
    -0.07
    er
    -0.07
     يس
    -0.07
     расстоя
    -0.07
     Age
    -0.07
    POSITIVE LOGITS
     protocol
    0.11
     protocols
    0.10
    .protocol
    0.09
     Protocol
    0.08
    pack
    0.07
     클
    0.07
     Holland
    0.07
    _protocol
    0.07
    /documentation
    0.07
    (pkt
    0.07
    Act Density 0.012%

    No Known Activations