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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia excerpts/references

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on multi‐word proper names—place names, organizations, and other named entities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     squeezing
    -0.06
    电影
    -0.06
     гра
    -0.06
    	number
    -0.06
     segmented
    -0.06
    读
    -0.06
    Like
    -0.06
     widths
    -0.06
     declined
    -0.06
     програм
    -0.06
    POSITIVE LOGITS
     Arms
    0.07
    "default
    0.07
    reature
    0.06
    طقة
    0.06
     UClass
    0.06
    )&&
    0.06
    花
    0.06
    quiv
    0.06
     Accepted
    0.06
    RESULTS
    0.06
    Act Density 0.035%

    No Known Activations