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

    Neuronpedia

    INDEX
    Explanations

    tech and specific proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     धातु
    0.50
     నమోదు
    0.44
     kayıt
    0.44
     నే
    0.43
     متا
    0.42
     기대
    0.42
    ృష్టి
    0.42
     کې
    0.41
    陼
    0.41
     然后
    0.41
    POSITIVE LOGITS
     alternate
    0.43
    umer
    0.43
     analyzing
    0.43
     anterior
    0.40
    ayar
    0.40
    А
    0.40
    ल्
    0.39
    AG
    0.39
    光
    0.39
    IC
    0.38
    Act Density 0.007%

    No Known Activations