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

    Neuronpedia

    INDEX
    Explanations

    generative models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Samuel
    0.48
     Fri
    0.44
     Olivia
    0.44
     Dau
    0.44
    uel
    0.43
     H
    0.42
     Naz
    0.42
     Да
    0.42
     Denmark
    0.41
     Solomon
    0.41
    POSITIVE LOGITS
    Ა
    0.46
     tidigare
    0.45
     فاتت
    0.45
    CIES
    0.44
     pijn
    0.44
    Evil
    0.43
    বিধা
    0.42
    рін
    0.42
    ඇ
    0.42
    ኣ
    0.42
    Act Density 0.000%

    No Known Activations