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

    Neuronpedia

    INDEX
    Explanations

    these spikes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    体系
    0.56
    ᆼ
    0.49
    ،
    0.47
    従
    0.43
    形態
    0.38
      
    0.38
     प्रयोग
    0.38
    ズル
    0.38
     प्रदर्शन
    0.38
     IEnumerable
    0.38
    POSITIVE LOGITS
     browned
    0.53
     embroiled
    0.51
     cinci
    0.51
     stallion
    0.51
     tinted
    0.51
     posta
    0.50
     acquitted
    0.50
     charred
    0.50
    news
    0.49
     intrepid
    0.49
    Act Density 0.000%

    No Known Activations