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

    Neuronpedia

    INDEX
    Explanations

    address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    इनस
    0.42
     Optim
    0.41
    斂
    0.40
    តម្លៃ
    0.39
     aportar
    0.39
    哎
    0.39
     نش
    0.38
    唉
    0.38
     Esc
    0.38
     anteriores
    0.37
    POSITIVE LOGITS
     Address
    0.91
     address
    0.86
    Address
    0.86
    address
    0.82
    Adress
    0.81
     addr
    0.76
     ADDRESS
    0.75
     адрес
    0.73
     addresses
    0.69
     地址
    0.69
    Act Density 0.010%

    No Known Activations