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

    Neuronpedia

    INDEX
    Explanations

    eye, RAM, eligible, odd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    о
    0.31
     the
    0.29
    у
    0.29
    the
    0.29
    а
    0.28
    е
    0.28
    и
    0.27
    D
    0.26
     remarkably
    0.25
    S
    0.25
    POSITIVE LOGITS
     protéines
    0.28
     séparation
    0.28
    AutoStabilise
    0.28
    权重
    0.26
    UnderWater
    0.26
    gäng
    0.26
    gdock
    0.25
     diarrh
    0.25
     épaules
    0.25
    gä
    0.25
    Act Density 0.303%

    No Known Activations