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

    Neuronpedia

    INDEX
    Explanations

    clear lungs and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verhindern
    0.46
     intrans
    0.42
     exacerb
    0.41
     spiking
    0.40
     klanten
    0.39
     Spike
    0.39
     Geschichten
    0.39
     spike
    0.38
     pelanggan
    0.38
     spiked
    0.38
    POSITIVE LOGITS
    没有任何
    0.54
    没有什么
    0.53
     overall
    0.53
    overall
    0.52
    smooth
    0.52
    整体
    0.52
    Smooth
    0.51
    沒有
    0.50
    Overall
    0.50
     structurally
    0.48
    Act Density 0.015%

    No Known Activations