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

    Neuronpedia

    INDEX
    Explanations

    position coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     قبول
    0.52
     salaried
    0.50
     Housewives
    0.50
     signatories
    0.47
     salari
    0.47
     shameless
    0.47
     housewives
    0.46
     instytuc
    0.46
     অস্বীকার
    0.46
     procéd
    0.45
    POSITIVE LOGITS
     position
    1.08
    position
    1.05
    位置
    1.00
     distance
    0.97
    Position
    0.96
     positions
    0.94
     distances
    0.90
     location
    0.90
     위치
    0.89
    positions
    0.88
    Act Density 0.314%

    No Known Activations