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

    Neuronpedia

    INDEX
    Explanations

    programming databases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lıklar
    -0.07
     프랑스
    -0.06
     graduates
    -0.06
     REGION
    -0.06
    cação
    -0.06
     million
    -0.06
    ерин
    -0.06
     ещё
    -0.06
    油
    -0.06
     reg
    -0.06
    POSITIVE LOGITS
     {},↵
    0.06
     Krish
    0.06
    (coder
    0.06
     tất
    0.06
     текущ
    0.06
     debunk
    0.06
     sink
    0.06
    进
    0.06
     perror
    0.06
    Sending
    0.06
    Act Density 0.088%

    No Known Activations