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

    Neuronpedia

    INDEX
    Explanations

    oscilloscopes and data acquisition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flights
    0.49
     incidental
    0.43
    istors
    0.43
     Ya
    0.42
     ya
    0.42
     handic
    0.41
     calorie
    0.39
     seksual
    0.39
     Hatton
    0.39
     handicapped
    0.39
    POSITIVE LOGITS
    étape
    0.41
    ErrorMessage
    0.39
    Inn
    0.39
    InData
    0.39
    avgsalary
    0.37
    ੁੰ
    0.37
    穂
    0.37
    মিস্ট
    0.37
    MNumber
    0.37
    柿
    0.37
    Act Density 0.000%

    No Known Activations