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

    Neuronpedia

    INDEX
    Explanations

    football positions and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decena
    0.61
    槐
    0.60
    رات
    0.59
    ро
    0.59
    外
    0.59
    كبر
    0.58
    光
    0.58
     зовніш
    0.57
     свето
    0.57
    自分で
    0.55
    POSITIVE LOGITS
    am
    0.67
    ens
    0.62
    dard
    0.62
    ake
    0.60
    are
    0.59
     Hunts
    0.59
    ancock
    0.58
     scooters
    0.57
     meadow
    0.57
     Morty
    0.57
    Act Density 0.000%

    No Known Activations