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

    Neuronpedia

    INDEX
    Explanations

    US cities and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ال
    2.90
     tubers
    2.74
    ット
    2.70
    рі
    2.67
     výro
    2.64
     remarqu
    2.62
    ați
    2.60
    t
    2.56
    ی
    2.54
     começ
    2.52
    POSITIVE LOGITS
     والق
    2.59
    ोहित
    2.57
    वों
    2.55
    mare
    2.52
     dấu
    2.48
    fullName
    2.47
     получилось
    2.46
    crunch
    2.45
    popup
    2.42
    punctuation
    2.41
    Act Density 0.097%

    No Known Activations