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

    Neuronpedia

    INDEX
    Explanations

    the Trevor Project and National services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rings
    0.54
     chunky
    0.54
     weder
    0.54
     ismer
    0.52
     paralle
    0.52
     anillos
    0.52
    ហារ
    0.51
    গামী
    0.51
    ‚¬
    0.51
     beach
    0.50
    POSITIVE LOGITS
     National
    1.25
     Center
    1.15
     Institute
    1.08
    National
    1.04
     Association
    1.04
     Society
    1.02
     Office
    1.01
     Centre
    1.00
     International
    1.00
     Department
    0.92
    Act Density 0.104%

    No Known Activations