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

    Neuronpedia

    INDEX
    Explanations

    heterogeneity and uniformity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rowave
    0.59
    quakes
    0.45
     कौशिक
    0.45
    External
    0.44
    ğunu
    0.44
    ureka
    0.43
    ThoughtData
    0.43
     природных
    0.43
     நடவடிக்கைகள்
    0.43
    leaning
    0.43
    POSITIVE LOGITS
     clustered
    0.51
    ᆼ
    0.51
     nella
    0.49
     dalam
    0.49
    Dalam
    0.46
     estremamente
    0.45
     TER
    0.44
     Dalam
    0.44
     biri
    0.44
     nelle
    0.43
    Act Density 0.004%

    No Known Activations