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

    Neuronpedia

    INDEX
    Explanations

    street and area names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    梼
    0.51
     flavorful
    0.49
     YAML
    0.47
     XY
    0.46
     uname
    0.45
     Conceptual
    0.45
    熒
    0.45
     できる
    0.45
     își
    0.44
     immutable
    0.44
    POSITIVE LOGITS
     Coronation
    0.69
     Meadow
    0.65
     Vicar
    0.62
     Church
    0.61
     Manor
    0.61
     Stoke
    0.60
     Grange
    0.60
     allotments
    0.59
     Junction
    0.58
     junction
    0.58
    Act Density 0.004%

    No Known Activations