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

    Neuronpedia

    INDEX
    Explanations

    detecting issues and predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oldsymbol
    0.43
     вече
    0.42
    ären
    0.42
    煂
    0.41
    绿色
    0.40
    érica
    0.39
     общества
    0.39
    рия
    0.39
    促进
    0.39
    ربعة
    0.39
    POSITIVE LOGITS
     ancillary
    0.49
    P
    0.48
    پ
    0.46
     issue
    0.46
     Sichuan
    0.45
     serialization
    0.45
    V
    0.45
     medici
    0.45
    ルコ
    0.44
     repatriation
    0.44
    Act Density 0.000%

    No Known Activations