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

    Neuronpedia

    INDEX
    Explanations

    operations and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Seç
    0.44
     язы
    0.42
     அனுமதி
    0.40
     précisément
    0.40
    寢
    0.39
     言
    0.39
    riert
    0.39
    рі
    0.38
     છીએ
    0.38
    튿
    0.38
    POSITIVE LOGITS
     multiplications
    0.49
     globalization
    0.48
     interruptions
    0.46
     catastrophes
    0.46
     Globalization
    0.44
    Globalization
    0.43
     dives
    0.43
     improper
    0.41
     calamities
    0.41
     migliore
    0.40
    Act Density 0.003%

    No Known Activations