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

    Neuronpedia

    INDEX
    Explanations

    Meta-analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Đồng
    0.73
     Synod
    0.73
    redi
    0.73
    ﹊
    0.70
    ridas
    0.69
    ydı
    0.68
    menuStrip
    0.68
    úd
    0.66
    itol
    0.66
    čiu
    0.66
    POSITIVE LOGITS
     cognition
    0.92
     AI
    0.90
     औपचारिक
    0.83
    llama
    0.79
     Kigali
    0.76
    認知
    0.76
     ISA
    0.76
     ওয়
    0.75
     rut
    0.75
     sarcasm
    0.74
    Act Density 0.009%

    No Known Activations