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

    Neuronpedia

    INDEX
    Explanations

    Linq queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tights
    0.76
     surrounding
    0.74
    Aur
    0.72
     май
    0.70
     surrounds
    0.70
     compartmental
    0.68
     Dressing
    0.66
     센
    0.66
     Cand
    0.65
     ग्रेजुएशन
    0.65
    POSITIVE LOGITS
    query
    1.14
     queries
    1.07
     query
    1.02
     বীজ
    1.01
     consulta
    0.98
     expresiones
    0.97
     lambda
    0.95
    Query
    0.92
    lambda
    0.90
     Queries
    0.89
    Act Density 0.002%

    No Known Activations