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

    Neuronpedia

    INDEX
    Explanations

    orientation and position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    還有
    0.76
     еще
    0.75
     علاوہ
    0.73
    Homemade
    0.72
    sud
    0.71
    Colorado
    0.71
    Basic
    0.70
    Har
    0.70
    Haus
    0.69
    Hundreds
    0.69
    POSITIVE LOGITS
     orientated
    0.86
     drinkers
    0.75
     পিডিএফ
    0.75
     drinking
    0.74
    టై
    0.71
     beverages
    0.70
     உதய
    0.70
     galleries
    0.70
     naturalist
    0.70
     conservation
    0.70
    Act Density 0.018%

    No Known Activations