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

    Neuronpedia

    INDEX
    Explanations

    magnet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     THINK
    -0.07
    itizen
    -0.07
    ôn
    -0.07
    네요
    -0.07
    niční
    -0.06
    وية
    -0.06
    groupBy
    -0.06
    ."
    -0.06
    งของ
    -0.06
    \"></
    -0.06
    POSITIVE LOGITS
     trafficking
    0.07
    _EXCEPTION
    0.07
    _PROPERTIES
    0.07
    Enumer
    0.06
     Sapphire
    0.06
     signing
    0.06
     Entrepreneur
    0.06
    -runner
    0.06
     Serv
    0.06
    .Does
    0.06
    Act Density 0.001%

    No Known Activations