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

    Neuronpedia

    INDEX
    Explanations

    medical treatments and AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    枻
    0.45
    Kentucky
    0.42
    的产品
    0.42
    पेयी
    0.42
    тельный
    0.40
    끅
    0.40
     अफ
    0.38
     отказыва
    0.38
     giây
    0.38
     Finals
    0.38
    POSITIVE LOGITS
    ừa
    0.45
     seven
    0.44
    upt
    0.42
    seven
    0.42
     Initial
    0.41
     initial
    0.40
     پرا
    0.40
     SVM
    0.39
     armor
    0.39
     Ml
    0.39
    Act Density 0.000%

    No Known Activations