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

    Neuronpedia

    INDEX
    Explanations

    eating and restaurants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.52
    ून
    1.40
    HttpServlet
    1.17
     perror
    1.14
     لازم
    1.12
    QtWidgets
    1.11
    پار
    1.11
    তা
    1.08
    党员
    1.07
    या
    1.07
    POSITIVE LOGITS
     dov
    1.10
    கிர
    1.07
     Nbd
    1.06
    aneous
    1.00
     tamar
    0.99
    х
    0.98
    ضع
    0.98
    рани
    0.98
    斓
    0.94
     grouped
    0.93
    Act Density 0.035%

    No Known Activations