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

    Neuronpedia

    INDEX
    Explanations

    node and series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     School
    0.45
    実は
    0.42
     leagues
    0.42
     Hewlett
    0.41
     GHz
    0.41
     Attention
    0.41
     Schein
    0.41
     Elgin
    0.40
    疇
    0.40
     Seller
    0.39
    POSITIVE LOGITS
    node
    0.54
    ле
    0.51
    лесо
    0.48
    lado
    0.48
    cloudfront
    0.46
     फ्लाई
    0.45
    یا
    0.44
    सी
    0.44
    зі
    0.44
    ujemo
    0.44
    Act Density 0.001%

    No Known Activations