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

    Neuronpedia

    INDEX
    Explanations

    code snippets or documentation

    np_max-act · gemini-2.0-flash

    The neuron fires on the Russian noun suffix “-ность,” i.e. on abstract nouns formed with that ending.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Generic
    -0.07
     RAID
    -0.06
    _ajax
    -0.06
    .eof
    -0.06
     сут
    -0.06
    Morning
    -0.06
    /generated
    -0.06
    (blank
    -0.06
    Authors
    -0.06
     AccessToken
    -0.06
    POSITIVE LOGITS
     phân
    0.07
    -Co
    0.06
     MouseEvent
    0.06
    Ü
    0.06
     comprar
    0.06
    하다
    0.06
    UEL
    0.06
    κολ
    0.06
    čka
    0.06
     cậu
    0.06
    Act Density 0.001%

    No Known Activations