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

    Neuronpedia

    INDEX
    Explanations

    playing characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thats
    0.44
    ்ப்பு
    0.43
     interfered
    0.41
     Issa
    0.39
    PhotoImage
    0.38
    িয়নের
    0.38
    жем
    0.37
     Thats
    0.37
     impar
    0.37
     Rios
    0.37
    POSITIVE LOGITS
     Predator
    0.42
     увла
    0.41
     Tabs
    0.41
    tabs
    0.40
    eniendo
    0.40
    avasena
    0.39
    心态
    0.39
    criterion
    0.39
    নির্ব
    0.38
     Kristian
    0.38
    Act Density 0.000%

    No Known Activations