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

    Neuronpedia

    INDEX
    Explanations

    court sentences

    np_max-act · gemini-2.0-flash

    This neuron activates on legal sentencing details, especially numeric prison‐term mentions and consecutive‐serving language.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cmap
    -0.06
    ソ
    -0.06
    408
    -0.06
    _SA
    -0.06
    _pattern
    -0.06
    '][
    -0.06
     Andrews
    -0.06
     blends
    -0.06
    rema
    -0.06
    ball
    -0.06
    POSITIVE LOGITS
     khởi
    0.08
     характеристи
    0.08
    Measured
    0.07
    kad
    0.06
    NAMESPACE
    0.06
     heavenly
    0.06
     elek
    0.06
     progressively
    0.06
     порушення
    0.06
     ",");↵
    0.06
    Act Density 0.001%

    No Known Activations