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

    Neuronpedia

    INDEX
    Explanations

    seeking details about user context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innovations
    0.94
    ivores
    0.91
    rencies
    0.90
     beacons
    0.87
     syndromes
    0.87
    itates
    0.86
     crises
    0.86
    oxins
    0.85
     innovators
    0.85
    olecules
    0.83
    POSITIVE LOGITS
     iPhone
    1.07
     tengo
    1.06
     iPad
    1.04
     Macbook
    1.04
     MacBook
    1.03
     boyfriend
    0.96
     mám
    0.94
     laptop
    0.92
     Android
    0.90
     girlfriend
    0.89
    Act Density 0.085%

    No Known Activations