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

    Neuronpedia

    INDEX
    Explanations

    orcas, ovarian, odd, operating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    overs
    0.52
     ए
    0.41
    unload
    0.39
     apertura
    0.38
     آمر
    0.38
    Alessandro
    0.36
    ody
    0.36
     іх
    0.36
     Burj
    0.35
    addEventListener
    0.35
    POSITIVE LOGITS
     ông
    0.72
     ọ
    0.61
     ό
    0.60
     õ
    0.59
     odio
    0.58
     ओबीसी
    0.55
     obat
    0.54
     ও
    0.53
     oef
    0.53
     oven
    0.52
    Act Density 0.271%

    No Known Activations