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

    Neuronpedia

    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash

    This neuron responds to tokens that contain non‑ASCII/accented characters (letters with diacritics), i.e., foreign words and names.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    vida
    -0.08
     Federal
    -0.08
     фут
    -0.07
    코
    -0.07
    அ
    -0.07
    oop
    -0.07
    uos
    -0.07
    .Unlock
    -0.07
     something
    -0.07
     perfectly
    -0.06
    POSITIVE LOGITS
    (training
    0.07
    死者
    0.07
    此案
    0.07
    Remaining
    0.07
     Instantiate
    0.07
    تط
    0.06
    .minutes
    0.06
     useClass
    0.06
    各项工作
    0.06
     счит
    0.06
    Act Density 1.031%

    No Known Activations