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

    Neuronpedia

    INDEX
    Explanations

    materials and their forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🏦
    0.33
     фаразы
    0.32
     заслу
    0.32
    数据集
    0.30
    剧情
    0.30
    xcsche
    0.30
     inputArray
    0.29
     डेटा
    0.29
    觎
    0.29
     δή
    0.29
    POSITIVE LOGITS
     strips
    0.67
     plastic
    0.62
     cardboard
    0.57
     wire
    0.55
     nylon
    0.55
     polyethylene
    0.54
     cotton
    0.54
     clips
    0.54
     glue
    0.53
     strip
    0.53
    Act Density 0.145%

    No Known Activations