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

    Neuronpedia

    INDEX
    Explanations

    end of lists and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     C
    0.25
     AMAZING
    0.25
     Grammy
    0.24
     Sydney
    0.24
     hänen
    0.24
     his
    0.24
     R
    0.23
     months
    0.23
     खबरों
    0.23
     তৎকালীন
    0.23
    POSITIVE LOGITS
     thereof
    0.33
     тощо
    0.33
    deki
    0.31
    .
    0.31
     वगैरह
    0.30
    ။
    0.30
    。「
    0.30
     போன்றவை
    0.30
    。
    0.29
     and
    0.29
    Act Density 2.466%

    No Known Activations