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

    Neuronpedia

    INDEX
    Explanations

    network initialization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    List
    -0.08
    박
    -0.08
    Interop
    -0.08
    bund
    -0.07
    .List
    -0.07
     paket
    -0.07
    跨
    -0.07
     adquir
    -0.07
    ুপ
    -0.07
     blocs
    -0.07
    POSITIVE LOGITS
     initializing
    0.11
     seeds
    0.11
     初始化
    0.10
     randomly
    0.10
     Seeds
    0.10
     initializes
    0.10
    初始化
    0.10
    .initialize
    0.10
    Initializing
    0.10
     initialization
    0.10
    Act Density 0.002%

    No Known Activations