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

    Neuronpedia

    INDEX
    Explanations

    jupyter notebook code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
     mimic
    -0.07
    िलन
    -0.07
     яку
    -0.07
     이동합니다
    -0.07
    -0.07
    	setTimeout
    -0.06
     ardından
    -0.06
    cal
    -0.06
    -0.06
    POSITIVE LOGITS
     검
    0.09
    ynthesis
    0.07
    	range
    0.07
     murdered
    0.06
    тиров
    0.06
    VML
    0.06
    oseconds
    0.06
     =↵
    0.06
     kims
    0.06
     RESULTS
    0.06
    Act Density 0.038%

    No Known Activations