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

    Neuronpedia

    INDEX
    Explanations

    memory addresses and offsets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agr
    0.49
    ージャー
    0.41
    ancis
    0.40
     کشاور
    0.40
     మీడి
    0.40
    indu
    0.39
    部品
    0.39
    builders
    0.39
    scholar
    0.39
    agnes
    0.38
    POSITIVE LOGITS
    地址
    0.79
     memory
    0.74
    Offsets
    0.73
    Memory
    0.70
    内存
    0.70
     Memory
    0.68
    Address
    0.68
     offsets
    0.68
     addresses
    0.67
    Adress
    0.67
    Act Density 0.025%

    No Known Activations