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

    Neuronpedia

    INDEX
    Explanations

    ranges and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دو
    0.50
    两大
    0.47
     두
    0.46
     complej
    0.45
     deux
    0.45
     이슈
    0.45
     نوع
    0.44
     duas
    0.44
    缫
    0.42
    Dependencies
    0.42
    POSITIVE LOGITS
     ranging
    0.73
     values
    0.70
    values
    0.66
    ranging
    0.65
     successively
    0.65
     диапазо
    0.63
     incrementally
    0.60
     incremental
    0.59
     ranged
    0.59
     progressively
    0.58
    Act Density 0.172%

    No Known Activations