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

    Neuronpedia

    INDEX
    Explanations

    word classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    岖
    1.77
    どん
    1.59
    ς
    1.57
    EST
    1.55
     Werte
    1.55
     Unterschiede
    1.55
    ppure
    1.53
    popularity
    1.52
    ki
    1.52
    ں
    1.50
    POSITIVE LOGITS
    िक्ट
    2.16
    ول
    2.03
    om
    2.00
    ो
    1.96
    ী
    1.91
    اد
    1.88
    icción
    1.82
    рия
    1.80
     synonymous
    1.79
     remanded
    1.74
    Act Density 0.251%

    No Known Activations