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

    Neuronpedia

    INDEX
    Explanations

    print after set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nue
    0.42
    data
    0.40
     nue
    0.40
     remarque
    0.40
    nueva
    0.39
    protobuf
    0.38
    iji
    0.38
    メ
    0.37
    kafka
    0.37
    ри
    0.36
    POSITIVE LOGITS
     Precision
    0.49
     precision
    0.47
     printed
    0.47
     چاپ
    0.46
    打印
    0.45
     maxLength
    0.45
     print
    0.45
     printers
    0.45
     Printed
    0.45
    प्रिंट
    0.45
    Act Density 0.003%

    No Known Activations