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

    Neuronpedia

    INDEX
    Explanations

    ride is shared

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     astring
    0.96
     minuscule
    0.94
     diminutive
    0.92
     utilitarian
    0.92
     crumbling
    0.92
     quintessential
    0.90
     ubiquitous
    0.89
     abundant
    0.88
     gigantes
    0.87
     haphazard
    0.86
    POSITIVE LOGITS
    Detail
    1.03
    Details
    1.02
    Assessment
    0.99
    StartDate
    0.97
    Analytics
    0.96
     వివర
    0.95
    Group
    0.94
    Customer
    0.92
    Request
    0.92
    詳細
    0.91
    Act Density 0.854%

    No Known Activations