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

    Neuronpedia

    INDEX
    Explanations

    animals

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting date‐style expressions (e.g. month names, day numbers, and years).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     exposition
    -0.06
    icators
    -0.06
    教
    -0.06
    ician
    -0.06
     天
    -0.06
     našich
    -0.06
     Bout
    -0.06
    _DYNAMIC
    -0.06
     �
    -0.05
     автор
    -0.05
    POSITIVE LOGITS
    dız
    0.06
    -operative
    0.06
     distrib
    0.06
    Resistance
    0.06
    procs
    0.06
    (fig
    0.06
    .ID
    0.06
    try
    0.06
     останов
    0.06
    輔
    0.06
    Act Density 0.018%

    No Known Activations