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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash

    This neuron activates on adverbs ending in “-ly.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     seek
    -0.07
     Saturday
    -0.07
     Vanderbilt
    -0.07
     Modules
    -0.07
    .st
    -0.07
    098
    -0.06
    057
    -0.06
     ignores
    -0.06
    -length
    -0.06
     pageSize
    -0.06
    POSITIVE LOGITS
     eg
    0.07
    œ
    0.07
     tão
    0.07
     но
    0.06
     too
    0.06
    How
    0.06
    Too
    0.06
    HOW
    0.06
    acr
    0.06
    niž
    0.06
    Act Density 0.036%

    No Known Activations