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

    Neuronpedia

    INDEX
    Explanations

    Code special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    洞察
    -0.07
     learnt
    -0.07
    uros
    -0.07
     Amanda
    -0.07
     understood
    -0.07
    忘了
    -0.07
    节点
    -0.07
     datasets
    -0.07
     connected
    -0.06
    ų
    -0.06
    POSITIVE LOGITS
    为首
    0.07
    Ѽ
    0.07
     [.
    0.07
    htmlspecialchars
    0.07
     IndexError
    0.06
    [Y
    0.06
    嚄
    0.06
    roring
    0.06
     Search
    0.06
    殖
    0.06
    Act Density 0.012%

    No Known Activations