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

    Neuronpedia

    INDEX
    Explanations

    microscope

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “microscope” (including variations like “microscope‐like”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bag
    -0.07
      
    -0.07
    _Ad
    -0.07
     Flint
    -0.07
     Arr
    -0.07
    Rent
    -0.07
    a
    -0.06
     FAT
    -0.06
     Rent
    -0.06
     ad
    -0.06
    POSITIVE LOGITS
     microscope
    0.09
    oscope
    0.09
    roscope
    0.09
     telescope
    0.09
    osc
    0.08
    cope
    0.08
    oscopic
    0.07
    زه
    0.07
    ishop
    0.07
    Smoke
    0.07
    Act Density 0.012%

    No Known Activations