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

    Neuronpedia

    INDEX
    Explanations

    entrance and exit points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    漼
    0.88
    匡
    0.87
     प्लांट्स
    0.83
     таъ
    0.77
    奋斗
    0.76
     eosin
    0.76
     ని
    0.75
    缨
    0.75
    癌症
    0.74
    ява
    0.74
    POSITIVE LOGITS
     door
    2.11
     entrance
    2.02
     doors
    2.01
     Door
    1.96
     entrances
    1.96
     pintu
    1.92
    Door
    1.91
     gates
    1.90
     gate
    1.86
     Gate
    1.85
    Act Density 0.503%

    No Known Activations