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

    Neuronpedia

    INDEX
    Explanations

    removes pathogens and noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tex
    0.45
    聚集
    0.45
     Tattha
    0.44
     थक
    0.43
    merzen
    0.42
     разде
    0.41
     Textile
    0.41
     ಅಂಶ
    0.41
     That
    0.41
     Textiles
    0.41
    POSITIVE LOGITS
    N
    0.53
     lata
    0.49
    i
    0.48
    인
    0.46
    Sh
    0.45
    മാക്കി
    0.45
     astral
    0.45
    C
    0.45
     convivial
    0.45
    idy
    0.44
    Act Density 0.000%

    No Known Activations