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

    Neuronpedia

    INDEX
    Explanations

    Top Tier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ras
    0.39
     Pricing
    0.36
     bouncing
    0.36
    ικές
    0.36
     Ras
    0.36
    VIN
    0.35
     vectores
    0.35
    న్నా
    0.35
    ילו
    0.35
     nark
    0.34
    POSITIVE LOGITS
     slowly
    0.46
     Slowly
    0.45
    慢慢
    0.44
     jeho
    0.44
    他的
    0.43
     lentamente
    0.43
     lentement
    0.40
     धीरे
    0.39
     আস্তে
    0.39
     his
    0.39
    Act Density 0.000%

    No Known Activations