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

    Neuronpedia

    INDEX
    Explanations

    assembly instructions, registers, and addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    captivity
    0.46
    跨境
    0.45
    GEBURTS
    0.41
     sostenibilidad
    0.41
    branded
    0.40
    傘
    0.40
    streamlit
    0.40
     fjord
    0.40
     бассе
    0.39
     resale
    0.39
    POSITIVE LOGITS
     instruction
    1.08
     Instruction
    1.05
     Registers
    1.01
    地址
    1.00
     registers
    0.99
     address
    0.98
    Registers
    0.98
     Address
    0.97
     addresses
    0.96
    Instruction
    0.95
    Act Density 0.102%

    No Known Activations