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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Senator
    -0.08
    .getSimpleName
    -0.07
     Glover
    -0.07
    外观
    -0.07
     стрем
    -0.07
     Mojo
    -0.07
    ovsky
    -0.06
    虽
    -0.06
    (snapshot
    -0.06
     Nan
    -0.06
    POSITIVE LOGITS
    iron
    0.07
    ISyntaxException
    0.07
    (matrix
    0.07
    ypass
    0.07
    ⚁
    0.06
    wargs
    0.06
    Raises
    0.06
     bypass
    0.06
    dür
    0.06
    ycz
    0.06
    Act Density 0.059%

    No Known Activations