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

    Neuronpedia

    INDEX
    Explanations

    DE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DE
    -1.41
    DE
    -1.32
     De
    -1.16
    De
    -1.04
    range
    -1.02
    Range
    -0.99
     Range
    -0.91
    RANGE
    -0.80
     Del
    -0.74
     Де
    -0.64
    POSITIVE LOGITS
     Мексичка
    0.86
    存于互联网档案馆
    0.85
    WebVitals
    0.84
    Autoritní
    0.83
    BagLayout
    0.76
     becauſe
    0.75
    AddTagHelper
    0.74
     Majefty
    0.74
    neſs
    0.73
    ंदीखरीदारी
    0.72
    Act Density 1.869%

    No Known Activations