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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    οντας
    -0.09
     CDs
    -0.09
     statistically
    -0.08
    佩
    -0.08
     wearing
    -0.07
     purse
    -0.07
     Fig
    -0.07
     CD
    -0.07
    702
    -0.07
     intact
    -0.07
    POSITIVE LOGITS
     быстр
    0.08
     accelerating
    0.08
     иде
    0.08
     промышлен
    0.08
     infrastructure
    0.07
     Здесь
    0.07
    Infrastructure
    0.07
     accél
    0.07
     лак
    0.07
    Fuel
    0.07
    Act Density 0.004%

    No Known Activations