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

    Neuronpedia

    INDEX
    Explanations

    distance and proximity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interests
    1.01
     intereses
    0.94
    interests
    0.93
     Interests
    0.91
     restricting
    0.89
     suppressing
    0.88
     contests
    0.88
     পরিত
    0.87
    тивно
    0.87
     contest
    0.87
    POSITIVE LOGITS
    Distance
    1.48
    距离
    1.37
     jarak
    1.37
     distance
    1.35
    距離
    1.34
     distante
    1.33
     distanza
    1.31
     distância
    1.30
     Distance
    1.27
    distance
    1.27
    Act Density 0.402%

    No Known Activations