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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jong
    -0.07
     commands
    -0.06
     performed
    -0.06
    독
    -0.06
     disparities
    -0.06
     Natural
    -0.06
     Liberals
    -0.06
     konumu
    -0.06
    =UTF
    -0.06
    daughter
    -0.06
    POSITIVE LOGITS
     составе
    0.07
    _ALIGN
    0.07
     ortalama
    0.07
     coff
    0.06
     вари
    0.06
    ladım
    0.06
    sembles
    0.06
    exao
    0.06
     impl
    0.06
     OC
    0.06
    Act Density 0.103%

    No Known Activations