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

    Neuronpedia

    INDEX
    Explanations

    internet forum posts

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the definite article “the.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    诺
    -0.06
    ornado
    -0.06
    的小
    -0.06
    \Post
    -0.06
     mus
    -0.05
    ไลน
    -0.05
     trưởng
    -0.05
    positor
    -0.05
     κον
    -0.05
     navCtrl
    -0.05
    POSITIVE LOGITS
     libre
    0.07
    stackpath
    0.07
     Sponsored
    0.07
     Çağ
    0.07
     resembles
    0.06
    -olds
    0.06
    ,value
    0.06
    anth
    0.06
    .ACT
    0.06
     ac
    0.06
    Act Density 0.009%

    No Known Activations