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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    This neuron fires on the JSON key or literal string "idiom."

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bible
    -0.07
     سرعت
    -0.07
    رانی
    -0.07
    舗
    -0.06
    detalle
    -0.06
    óst
    -0.06
    _shapes
    -0.06
    �
    -0.06
     Bible
    -0.06
    [count
    -0.06
    POSITIVE LOGITS
     Regiment
    0.07
     并
    0.07
    mí
    0.06
     regimes
    0.06
    ht
    0.06
     experimented
    0.06
    emm
    0.06
     regime
    0.06
     doesn
    0.06
    configure
    0.06
    Act Density 0.002%

    No Known Activations