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

    Neuronpedia

    INDEX
    Explanations

    sum of, sum type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Comb
    0.45
    绸
    0.45
    卤
    0.44
     Komb
    0.42
     Spears
    0.42
    zens
    0.42
    ুৎ
    0.40
     Coom
    0.40
     Sauce
    0.40
     Edit
    0.39
    POSITIVE LOGITS
     sum
    0.67
    mation
    0.66
    matory
    0.60
    sum
    0.60
     maxSum
    0.57
     summation
    0.57
    Sum
    0.57
    ∑
    0.55
    ptuous
    0.54
     SUM
    0.54
    Act Density 0.011%

    No Known Activations