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

    Neuronpedia

    INDEX
    Explanations

    location within categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.21
    y
    1.15
    e
    1.12
    es
    1.09
    i
    1.05
    d
    1.04
    स
    1.02
    a
    0.96
    ↵
    0.94
    sand
    0.94
    POSITIVE LOGITS
     municipalities
    1.03
    مة
    0.99
     compartments
    0.98
     которые
    0.97
    られている
    0.96
     municípios
    0.96
    țele
    0.95
     rurales
    0.95
    뢨
    0.93
     України
    0.93
    Act Density 0.223%

    No Known Activations