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

    Neuronpedia

    INDEX
    Explanations

    swipe actions and shopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hány
    0.41
    ucible
    0.38
    alin
    0.38
     banter
    0.38
     erm
    0.37
     بيه
    0.37
    रेख
    0.37
     givenChar
    0.37
     facil
    0.37
     ceasefire
    0.36
    POSITIVE LOGITS
     swipe
    0.60
     Swipe
    0.57
     Shopping
    0.54
     shopping
    0.52
     swipes
    0.52
    Swipe
    0.51
    swipe
    0.50
    购物
    0.47
    shopping
    0.46
    Shopping
    0.45
    Act Density 0.003%

    No Known Activations