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

    Neuronpedia

    INDEX
    Explanations

    regulated industries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conscientes
    0.51
    曩
    0.46
     Bhajan
    0.46
     Đình
    0.45
     Прав
    0.45
     العالمية
    0.45
    quí
    0.44
     irresponsible
    0.44
    тит
    0.44
    bindingNavigator
    0.44
    POSITIVE LOGITS
     laundry
    0.45
     wine
    0.43
     vapor
    0.42
    Insurance
    0.41
    Y
    0.41
    ם
    0.41
    y
    0.41
     Wine
    0.41
     Insurance
    0.40
     duh
    0.39
    Act Density 0.004%

    No Known Activations