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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.61
     PowerShell
    0.55
    (
    0.54
     rek
    0.50
     reputation
    0.49
     (
    0.49
     tes
    0.48
     ponder
    0.48
     posse
    0.47
    -
    0.47
    POSITIVE LOGITS
    png
    0.69
    étrico
    0.67
     године
    0.64
     ಹಲವಾರು
    0.62
    aniach
    0.61
    jpg
    0.61
     Букмекер
    0.61
     yüzy
    0.60
     illetve
    0.60
    MenuItemView
    0.60
    Act Density 0.241%

    No Known Activations