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
     smallest
    -0.08
    er
    -0.08
     Eyes
    -0.08
    平方
    -0.07
     ster
    -0.07
    inder
    -0.07
    5
    -0.07
    348
    -0.07
     Fisher
    -0.07
     ز
    -0.07
    POSITIVE LOGITS
     protocol
    0.15
     protocols
    0.14
     Protocol
    0.12
    Protocol
    0.11
    protocol
    0.09
     Malcolm
    0.09
    .protocol
    0.09
    ocols
    0.08
    \uC
    0.08
    _protocol
    0.08
    Act Density 0.010%

    No Known Activations