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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ма
    0.99
    u
    0.98
    да
    0.96
    ors
    0.87
    olina
    0.86
     latéraux
    0.84
    iz
    0.82
     Plastic
    0.82
    acuda
    0.82
     màu
    0.80
    POSITIVE LOGITS
     summarize
    1.04
     গার্মেন্টস
    1.03
    👕
    1.00
    évaluation
    0.99
    👚
    0.98
     одежды
    0.96
     evaluation
    0.95
     econometric
    0.95
     idempotent
    0.95
     গার্ম
    0.95
    Act Density 0.009%

    No Known Activations