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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash

    The neuron detects references to human history or societal events over time—e.g. mentions of “throughout history,” “societies,” “conflicts,” and “violence.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    伦
    -0.07
    bbox
    -0.06
    仕事
    -0.06
     Beitrag
    -0.06
    144
    -0.06
    Undefined
    -0.06
    とき
    -0.06
     breakup
    -0.06
    confidence
    -0.06
     McKenzie
    -0.06
    POSITIVE LOGITS
     narr
    0.06
             
    0.06
    _MONTH
    0.06
    :A
    0.06
    iosa
    0.06
    τοι
    0.06
    road
    0.06
     domů
    0.06
    afka
    0.06
    pick
    0.06
    Act Density 0.074%

    No Known Activations