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

    Neuronpedia

    INDEX
    Explanations

    practical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     certification
    -0.07
     等
    -0.06
    iếu
    -0.06
     bass
    -0.06
     угод
    -0.06
     así
    -0.06
    lates
    -0.06
     given
    -0.06
    半
    -0.06
     DISP
    -0.06
    POSITIVE LOGITS
    .links
    0.07
    .Volume
    0.06
    .Diagnostics
    0.06
    になった
    0.06
    htm
    0.06
    _exit
    0.06
    Sizes
    0.06
    /js
    0.06
     td
    0.06
    .Core
    0.06
    Act Density 0.013%

    No Known Activations