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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     כש
    0.42
     නො
    0.40
     பழைய
    0.38
    arquia
    0.38
     Бер
    0.37
    тору
    0.37
    ativas
    0.36
     কোনো
    0.36
    denly
    0.36
    র্
    0.35
    POSITIVE LOGITS
     sut
    0.43
     cr
    0.39
     hous
    0.38
     strop
    0.37
     rape
    0.37
     fox
    0.36
     atac
    0.36
     dox
    0.36
     mcg
    0.35
     Syk
    0.35
    Act Density 0.080%

    No Known Activations