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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of geographic place names (cities, states, countries) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pear
    -0.07
     Pill
    -0.06
    (Bit
    -0.06
    玲
    -0.06
     Garland
    -0.06
    (fl
    -0.06
    'h
    -0.06
    .Bit
    -0.06
     Brewer
    -0.06
     Lester
    -0.06
    POSITIVE LOGITS
     uzav
    0.08
     Ге
    0.07
    .utc
    0.07
     ActivatedRoute
    0.07
     ویژه
    0.07
     повітря
    0.07
    -largest
    0.07
     thác
    0.07
    алося
    0.07
    �
    0.07
    Act Density 0.068%

    No Known Activations