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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ť
    1.08
     realización
    1.06
     Desar
    1.05
     comien
    1.03
    Как
    1.02
     bzw
    1.01
     Desenvolvimento
    1.01
     Bản
    1.00
     Proces
    0.98
     Ста
    0.98
    POSITIVE LOGITS
    j
    0.85
    kilometer
    0.85
     liters
    0.84
     consecutive
    0.83
     engraved
    0.82
     embroidered
    0.82
     numerical
    0.81
    enthal
    0.81
     kilometers
    0.81
    leetcode
    0.80
    Act Density 0.379%

    No Known Activations