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

    Neuronpedia

    INDEX
    Explanations

    geographic regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diagram
    0.33
    瞬间
    0.32
     générateur
    0.31
    是一个
    0.31
    电流
    0.30
     Journey
    0.30
    本质
    0.30
    是个
    0.29
    散热
    0.29
     Script
    0.29
    POSITIVE LOGITS
     region
    0.41
    region
    0.40
     neighbouring
    0.37
     neighboring
    0.36
     região
    0.34
     southern
    0.33
     регионе
    0.33
     north
    0.33
     eastern
    0.32
     northern
    0.32
    Act Density 0.073%

    No Known Activations