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

    Neuronpedia

    INDEX
    Explanations

    management structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sw
    0.41
     Citizenship
    0.41
     Hero
    0.40
     dram
    0.40
     अग्रणी
    0.40
     whopping
    0.40
     world
    0.40
     Death
    0.39
     Hardware
    0.39
     Ath
    0.39
    POSITIVE LOGITS
    層
    0.54
    层的
    0.53
    층
    0.52
     STRUCTURE
    0.49
    层
    0.48
    Structure
    0.47
    strukt
    0.46
     kurulu
    0.45
     cadre
    0.45
     структура
    0.45
    Act Density 0.011%

    No Known Activations