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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heapq
    -0.07
    ζα
    -0.07
     Зам
    -0.07
    dictionary
    -0.06
    章
    -0.06
     submodule
    -0.06
    -created
    -0.06
     OTHERWISE
    -0.06
    ffff
    -0.06
    .AddDays
    -0.06
    POSITIVE LOGITS
     adher
    0.07
     director
    0.07
     示例
    0.07
    σιο
    0.06
    _des
    0.06
    pper
    0.06
     multic
    0.06
    Mit
    0.06
    -Compatible
    0.06
     الي
    0.06
    Act Density 0.369%

    No Known Activations