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

    Neuronpedia

    INDEX
    Explanations

    Here's how to solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сложные
    0.45
     opdracht
    0.42
     चढ़ा
    0.41
    \}=
    0.40
     실패
    0.39
     mauvais
    0.39
    특히
    0.39
     सबकुछ
    0.39
    今まで
    0.38
     failures
    0.38
    POSITIVE LOGITS
     werd
    0.39
     assumed
    0.38
    бет
    0.37
     বোধ
    0.37
     monochromatic
    0.36
     sole
    0.35
     Terrace
    0.34
     لنا
    0.34
     aé
    0.34
     anu
    0.34
    Act Density 0.003%

    No Known Activations