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

    Neuronpedia

    INDEX
    Explanations

    Code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ests
    -0.07
     ace
    -0.07
    ukes
    -0.06
    esters
    -0.06
    益
    -0.06
    /gcc
    -0.06
     Wien
    -0.06
    .results
    -0.06
    ratings
    -0.06
    号
    -0.06
    POSITIVE LOGITS
     Semantic
    0.08
    _rsa
    0.07
    았
    0.07
    	ar
    0.07
    {};↵
    0.07
     restrain
    0.07
     command
    0.07
    (gcf
    0.06
     Brain
    0.06
    (inertia
    0.06
    Act Density 0.002%

    No Known Activations