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

    Neuronpedia

    INDEX
    Explanations

    control flow keywords followed by semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palust
    0.43
    াসী
    0.42
    ACT
    0.41
     चाहिँ
    0.41
     hem
    0.39
    셔서
    0.39
     Hemsworth
    0.39
    বল
    0.38
    dery
    0.38
    של
    0.37
    POSITIVE LOGITS
    ;
    0.50
    ;;
    0.45
    而是
    0.40
     ;
    0.39
     ensues
    0.38
     anyway
    0.36
     UNIVERSITY
    0.36
     Anyway
    0.36
     بلکہ
    0.36
     tampoco
    0.36
    Act Density 0.012%

    No Known Activations