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

    Neuronpedia

    INDEX
    Explanations

    engine configurations

    np_max-act · gemini-2.0-flash

    This neuron detects specifications of engine configurations, especially numeric displacement values paired with cylinder counts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Teil
    -0.07
     서울특별시
    -0.07
     rollout
    -0.06
    .Designer
    -0.06
     paran
    -0.06
     parseInt
    -0.06
     걸
    -0.06
    miştir
    -0.06
    EntryPoint
    -0.06
    uglify
    -0.06
    POSITIVE LOGITS
    boat
    0.07
    Automatic
    0.07
     nắng
    0.06
     mounted
    0.06
     Ez
    0.06
    ”
    0.06
     FOUR
    0.06
    ン�
    0.06
    Y
    0.06
     iv
    0.06
    Act Density 0.010%

    No Known Activations