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

    Neuronpedia

    INDEX
    Explanations

    Numbers and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     υπηρε
    -0.07
    ์โ
    -0.06
    olume
    -0.06
    HasKey
    -0.06
     coastline
    -0.06
    几个
    -0.06
    นม
    -0.06
     mı
    -0.06
     tut
    -0.06
     환산
    -0.06
    POSITIVE LOGITS
    acet
    0.06
     conducted
    0.06
    annotation
    0.06
     تحص
    0.06
    QUAL
    0.06
                              ↵
    0.06
    @pytest
    0.06
    "))))↵
    0.06
     cancelling
    0.06
    मक
    0.06
    Act Density 0.008%

    No Known Activations