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

    Neuronpedia

    INDEX
    Explanations

    live, living, life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MNIST
    0.34
    onuclease
    0.33
    rikes
    0.33
     registrer
    0.33
    ipedi
    0.33
    ifices
    0.32
    咥
    0.32
    ड़की
    0.32
    ordia
    0.32
     रोकता
    0.32
    POSITIVE LOGITS
     living
    3.88
    living
    3.47
     Living
    3.45
    Living
    3.45
     lived
    3.39
     жи
    3.25
     sống
    3.19
     LIVING
    3.19
     живе
    3.13
     live
    3.11
    Act Density 0.148%

    No Known Activations