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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chromosomes
    -0.07
     Bars
    -0.06
    alyze
    -0.06
     Maintenance
    -0.06
     Robertson
    -0.06
     方法
    -0.06
    Clean
    -0.06
    Pes
    -0.06
     instituted
    -0.06
    haul
    -0.06
    POSITIVE LOGITS
     Label
    0.07
     BuzzFeed
    0.07
    .neo
    0.06
    /String
    0.06
     bajo
    0.06
    Hotel
    0.06
     přímo
    0.06
    ](
    0.06
     Romanian
    0.06
    ulario
    0.06
    Act Density 0.042%

    No Known Activations