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

    Neuronpedia

    INDEX
    Explanations

    animals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ינט
    -0.08
    יפה
    -0.08
    ТИ
    -0.08
    ต่ำ
    -0.08
     maks
    -0.08
    ต้อง
    -0.08
     manuf
    -0.08
     reckon
    -0.08
     realiseren
    -0.08
     fon
    -0.08
    POSITIVE LOGITS
    Experiment
    0.10
     Experiment
    0.09
     experiment
    0.09
    实验
    0.09
     maca
    0.09
    atest
    0.08
    experiment
    0.08
     backups
    0.08
    uzzo
    0.08
     प्रयोग
    0.08
    Act Density 0.002%

    No Known Activations