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

    Neuronpedia

    INDEX
    Explanations

    Technical information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =
    -0.06
    (
    -0.06
     Renaissance
    -0.06
     communicating
    -0.06
    的
    -0.06
     يتم
    -0.06
     emphasizes
    -0.06
    -0.06
     في
    -0.06
     Scott
    -0.06
    POSITIVE LOGITS
    ọ́
    0.09
     leor
    0.09
     lớp
    0.09
     hiểu
    0.09
     gebru
    0.09
     bør
    0.08
     líon
    0.08
     голове
    0.08
     aly
    0.08
     bida
    0.08
    Act Density 0.113%

    No Known Activations