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

    Neuronpedia

    INDEX
    Explanations

    Qt framework C++ code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     гум
    -0.06
    BAL
    -0.06
     adversity
    -0.06
    部分
    -0.06
     Reputation
    -0.06
     loại
    -0.06
     PCB
    -0.06
     Panc
    -0.06
     SCAN
    -0.06
    ️
    -0.06
    POSITIVE LOGITS
     Underground
    0.07
     slog
    0.06
    outed
    0.06
     Basis
    0.06
    .It
    0.06
     Ave
    0.06
    ovky
    0.06
     grabbing
    0.06
    //{↵
    0.06
    unless
    0.06
    Act Density 0.001%

    No Known Activations