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

    Neuronpedia

    INDEX
    Explanations

    proposals and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Change
    0.46
     પડશે
    0.43
     rằng
    0.43
    izing
    0.42
    izer
    0.42
    Complete
    0.42
    Seat
    0.42
    Sensitivity
    0.41
    Dinner
    0.41
    Meetings
    0.40
    POSITIVE LOGITS
     underprivileged
    0.48
     handicapped
    0.46
     Überblick
    0.44
    ᇂ
    0.44
     kumar
    0.43
     marginalised
    0.43
     pedestrians
    0.42
     surveyors
    0.42
     excelled
    0.41
     commodities
    0.41
    Act Density 0.002%

    No Known Activations