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

    Neuronpedia

    INDEX
    Explanations

    accumulating items in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сі
    0.38
    Ľ
    0.38
    矨
    0.37
     торже
    0.36
     avete
    0.36
     amare
    0.36
     গোলে
    0.36
     résoudre
    0.36
     नेहमी
    0.36
     ሁ
    0.35
    POSITIVE LOGITS
     accumulating
    0.73
    Accum
    0.70
    append
    0.67
     appending
    0.66
    どんどん
    0.65
     accumulator
    0.64
     accumulates
    0.64
     Accum
    0.63
     accum
    0.62
     append
    0.61
    Act Density 0.129%

    No Known Activations