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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    569
    -0.07
    293
    -0.07
    328
    -0.06
    看看
    -0.06
    ichael
    -0.06
     Rush
    -0.06
     rotterdam
    -0.06
    ăm
    -0.06
    226
    -0.06
    -shared
    -0.06
    POSITIVE LOGITS
                            
↵
    0.07
    andes
    0.06
     meisten
    0.06
     Mer
    0.06
    lyph
    0.06
    änn
    0.06
    eta
    0.06
     murderous
    0.06
    accur
    0.06
    _duration
    0.06
    Act Density 0.006%

    No Known Activations