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

    Neuronpedia

    INDEX
    Explanations

    lists of items or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    पीएससी
    0.44
     attenuate
    0.41
     vulgaris
    0.41
     heterogeneity
    0.39
     раді
    0.39
    กำลัง
    0.39
     interstitials
    0.39
     attenuated
    0.39
    DbContext
    0.38
    Infrastructure
    0.38
    POSITIVE LOGITS
     Crude
    0.42
     Mais
    0.42
     Lawson
    0.40
     G
    0.39
     M
    0.38
     B
    0.38
     Chiến
    0.38
     D
    0.38
     Depois
    0.38
     Alas
    0.38
    Act Density 0.001%

    No Known Activations