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

    Neuronpedia

    INDEX
    Explanations

    Based

    np_max-act · gemini-2.0-flash

    This neuron fires on first‐person self‐references—especially the pronoun “I” when the author expresses personal opinions or experiences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "',↵
    -0.06
    .sim
    -0.06
    ète
    -0.06
     individ
    -0.06
    AAAAAAAA
    -0.06
    жен
    -0.06
     sadd
    -0.06
    _gr
    -0.06
    (mm
    -0.06
    -os
    -0.06
    POSITIVE LOGITS
     توسعه
    0.07
     Stef
    0.06
     consenting
    0.06
     ตำ
    0.06
     rozhod
    0.06
     Cloth
    0.06
    �
    0.06
    dns
    0.06
     dobu
    0.06
    Resize
    0.06
    Act Density 0.049%

    No Known Activations