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

    Neuronpedia

    INDEX
    Explanations

    but and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ন্টার
    0.42
    ͙
    0.40
     शहरा
    0.39
     ഭരണ
    0.38
     정사각형
    0.38
     GraphQL
    0.38
     ডিজাইন
    0.37
     estructural
    0.37
     दिल्ली
    0.37
    原创
    0.37
    POSITIVE LOGITS
    茶
    0.37
    WER
    0.37
     acidification
    0.37
     اش
    0.37
    SIL
    0.36
    Ach
    0.35
     hohen
    0.35
    瞬
    0.35
     feathered
    0.34
     tí
    0.34
    Act Density 0.001%

    No Known Activations