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

    Neuronpedia

    INDEX
    Explanations

    devices and their functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ведения
    0.33
    явля
    0.31
    мера
    0.31
    หาย
    0.31
    ौरा
    0.30
    immersive
    0.30
    umap
    0.30
    িল্লী
    0.30
    Gray
    0.30
    ({},
    0.30
    POSITIVE LOGITS
     outputs
    0.49
     malfunction
    0.47
     output
    0.46
     작동
    0.45
     operated
    0.44
     manufacturer
    0.44
     usage
    0.43
     servicing
    0.42
     malfunctions
    0.42
     uptime
    0.41
    Act Density 0.082%

    No Known Activations