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

    Neuronpedia

    INDEX
    Explanations

    find your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pou
    0.40
     pou
    0.38
     सिक
    0.36
     пу
    0.36
     धार
    0.34
     otr
    0.34
     pu
    0.34
     latar
    0.34
    bast
    0.34
    CER
    0.34
    POSITIVE LOGITS
    Rational
    0.44
    कर्मियों
    0.42
    ِمض
    0.41
     racional
    0.40
    कर्मी
    0.40
    ="@+
    0.40
    ர்களுக்கு
    0.38
     Rational
    0.38
     सपा
    0.38
     Jets
    0.38
    Act Density 0.001%

    No Known Activations