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

    Neuronpedia

    INDEX
    Explanations

    often used to describe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gonz
    0.52
     Montana
    0.49
     Rachel
    0.48
     Antoine
    0.48
     microSD
    0.48
     Tiffany
    0.48
     Georgia
    0.47
     Mikey
    0.47
     Caleb
    0.47
     Verme
    0.47
    POSITIVE LOGITS
     आग
    0.44
     indivíduos
    0.41
    ục
    0.41
     indo
    0.40
     augment
    0.40
     تعلیم
    0.40
    ræ
    0.39
     사고
    0.38
    ورسٹی
    0.38
    다고
    0.38
    Act Density 0.001%

    No Known Activations