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

    Neuronpedia

    INDEX
    Explanations

    percentage discount offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ส์
    1.71
    ਰ
    1.70
     amide
    1.65
    ு
    1.63
     única
    1.62
     influent
    1.61
    \;
    1.58
    -\
    1.57
    1.56
     unica
    1.56
    POSITIVE LOGITS
     продукции
    1.84
    ember
    1.50
    ዖ
    1.46
    ২২
    1.40
    ఫ
    1.38
    ى
    1.34
    ig
    1.31
    est
    1.30
    ib
    1.28
     ጥቅም
    1.27
    Act Density 0.009%

    No Known Activations