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

    Neuronpedia

    INDEX
    Explanations

    overall comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    または
    0.50
     เกี่ยว
    0.48
     длиной
    0.48
     또는
    0.45
     सैकड़ों
    0.45
     Various
    0.44
     különböz
    0.44
    ๒
    0.43
     અથવા
    0.43
     다양한
    0.42
    POSITIVE LOGITS
     overall
    0.76
     comparison
    0.59
     average
    0.59
     most
    0.58
    整體
    0.57
    overall
    0.56
     aggregate
    0.55
     sectors
    0.54
    Overall
    0.54
    整体
    0.54
    Act Density 0.018%

    No Known Activations