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

    Neuronpedia

    INDEX
    Explanations

    wholesaling and wholly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    い
    3.41
    ை
    2.77
    客様
    2.52
    ১৪
    2.39
    ১৮
    2.36
    هي
    2.36
    ج
    2.30
    いや
    2.27
    브
    2.27
    ้
    2.22
    POSITIVE LOGITS
    hearted
    2.06
    kts
    2.05
    k
    1.91
     grosses
    1.79
     functors
    1.75
     garages
    1.70
     vapors
    1.69
     multiplets
    1.69
     hybrids
    1.68
    izers
    1.67
    Act Density 0.011%

    No Known Activations