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

    Neuronpedia

    INDEX
    Explanations

    Russian legal and programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    􀂃
    0.39
     हेल्दी
    0.35
     κάτι
    0.34
     Decedent
    0.33
     cowboys
    0.33
     দারুণ
    0.33
     Cowboys
    0.32
    affeine
    0.32
    প্তাহ
    0.32
    ลูกค้า
    0.32
    POSITIVE LOGITS
     Ш
    0.27
     М
    0.27
     Д
    0.26
    с
    0.26
     Аб
    0.26
     У
    0.26
    М
    0.26
     С
    0.25
    С
    0.25
     Ма
    0.25
    Act Density 6.819%

    No Known Activations