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

    Neuronpedia

    INDEX
    Explanations

    in specific locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     йөк
    0.37
     aggravation
    0.35
     наличи
    0.35
     ceva
    0.35
    ياب
    0.35
     л
    0.32
     왼
    0.32
    的想法
    0.32
    something
    0.31
     présence
    0.31
    POSITIVE LOGITS
     repositories
    0.67
     marketplaces
    0.64
     databases
    0.64
     hospitals
    0.62
     libraries
    0.62
     landfills
    0.62
     shrines
    0.62
     mosques
    0.61
     crowded
    0.61
     reservoirs
    0.61
    Act Density 0.074%

    No Known Activations