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

    Neuronpedia

    INDEX
    Explanations

    named entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mechan
    0.74
    Stre
    0.74
    (
    0.74
    instagood
    0.72
    (\
    0.68
    Being
    0.66
     notori
    0.63
    Advantages
    0.63
     desvent
    0.62
    Properties
    0.61
    POSITIVE LOGITS
     overseeing
    0.98
     supervising
    0.88
    ವರು
    0.82
     specialists
    0.80
     oversee
    0.80
     seniors
    0.79
     มอง
    0.79
    他们
    0.75
     ಅವರು
    0.75
     briefings
    0.74
    Act Density 0.093%

    No Known Activations