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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of scientific study types and research reports (e.g., systematic reviews, meta‐analyses, retrospective or prospective studies).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sciences
    -0.07
     free
    -0.07
     Robots
    -0.06
     viewpoints
    -0.06
     Cottage
    -0.06
     получ
    -0.06
    Independent
    -0.06
    Tank
    -0.06
    Human
    -0.06
    린
    -0.06
    POSITIVE LOGITS
     redistribute
    0.07
     ime
    0.07
     ฿
    0.06
     DDR
    0.06
    参加
    0.06
    сього
    0.06
     졸
    0.06
    /popper
    0.06
     nebu
    0.06
    _ty
    0.06
    Act Density 0.026%

    No Known Activations