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

    Neuronpedia

    INDEX
    Explanations

    Frontend component boilerplate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    רי
    0.43
     очередной
    0.41
    uds
    0.40
    ived
    0.39
     congratulations
    0.39
     angrily
    0.39
     congrat
    0.39
    owska
    0.38
    igration
    0.38
     intensified
    0.38
    POSITIVE LOGITS
     durchaus
    0.45
     sparsim
    0.45
     розви
    0.44
     réel
    0.43
     Neuroscience
    0.43
     découverte
    0.42
     interdiscipl
    0.42
     udvik
    0.41
     utvik
    0.41
     périodes
    0.41
    Act Density 0.003%

    No Known Activations