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

    Neuronpedia

    INDEX
    Explanations

    unique and unexpected occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Impl
    0.62
     entsprechende
    0.60
    Comparable
    0.59
    Moderate
    0.59
    Area
    0.59
    Estimate
    0.58
    Professional
    0.57
    П
    0.56
    Business
    0.56
    plus
    0.56
    POSITIVE LOGITS
     discoveries
    1.15
     quirks
    1.10
     revelations
    1.02
     inventions
    1.00
     experiences
    0.98
     quirk
    0.94
     dilemmas
    0.93
     happenings
    0.91
     juxt
    0.91
     adventures
    0.90
    Act Density 0.468%

    No Known Activations