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

    Neuronpedia

    INDEX
    Explanations

    period punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on the “NotImplementedError” exception message, i.e. it detects occurrences of that specific error name.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gauss
    -0.07
    DOG
    -0.07
    只有
    -0.07
    門
    -0.07
    home
    -0.06
    .DOM
    -0.06
    ่ง
    -0.06
    _wave
    -0.06
    庭
    -0.06
     спас
    -0.06
    POSITIVE LOGITS
    ++);↵
    0.07
     hton
    0.07
     UPDATE
    0.07
    ())),↵
    0.06
    /react
    0.06
    ○
    0.06
    );
↵
↵
    0.06
    ！」↵↵
    0.06
     INA
    0.06
    ")
↵
↵
    0.06
    Act Density 0.071%

    No Known Activations