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

    Neuronpedia

    INDEX
    Explanations

    gather, aggregate, combine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     direttamente
    0.45
     directamente
    0.42
     varje
    0.42
     directement
    0.42
    directly
    0.42
     diretamente
    0.41
     dupla
    0.40
     directly
    0.38
     hver
    0.38
     chacun
    0.38
    POSITIVE LOGITS
     একত্রিত
    1.09
     gathered
    1.02
     объеди
    1.02
     consolidate
    1.01
     together
    0.98
     into
    0.96
     एकत्र
    0.95
     एकत्रित
    0.93
     consolidating
    0.93
    が集
    0.93
    Act Density 0.049%

    No Known Activations