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

    Neuronpedia

    INDEX
    Explanations

    load

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Tower
    -0.07
     tower
    -0.07
     Traditional
    -0.07
     Bah
    -0.07
    传统
    -0.07
     father
    -0.07
    source
    -0.07
    union
    -0.07
    ọrọ
    -0.07
    POSITIVE LOGITS
    /init
    0.11
     থেকেই
    0.11
    加载
    0.11
     initializes
    0.11
     inicial
    0.10
    初始化
    0.10
     iniz
    0.10
     initialization
    0.10
     初始化
    0.10
    -loading
    0.10
    Act Density 0.013%

    No Known Activations