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

    Neuronpedia

    INDEX
    Explanations

    Problem-solving and reasoning systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ತೆರ
    -0.11
     ,
↵
    -0.09
    რკ
    -0.09
     снять
    -0.09
     આર
    -0.08
     მხარდაჭ
    -0.08
    վա
    -0.08
    ก็
    -0.08
     მონაწილ
    -0.08
     Гэта
    -0.08
    POSITIVE LOGITS
     GPT
    0.10
     Chat
    0.10
    Assistant
    0.09
    GPT
    0.09
     IELTS
    0.08
     imaginative
    0.08
     assistant
    0.08
     formatting
    0.08
     imagining
    0.08
     HTML
    0.07
    Act Density 0.109%

    No Known Activations