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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    consistency between a summary and its corresponding document.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron is effectively inactive—it does not reliably detect or respond to any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .unknown
    -0.07
     Anaheim
    -0.07
    PostMapping
    -0.06
     Tencent
    -0.06
     Prefix
    -0.06
    _orders
    -0.06
     Houston
    -0.06
     extrapol
    -0.06
     Glas
    -0.06
     Scoped
    -0.06
    POSITIVE LOGITS
     بشر
    0.06
    extField
    0.06
    віт
    0.06
    ง
    0.06
     δύο
    0.06
     antes
    0.06
    IGO
    0.06
     jScrollPane
    0.06
     ще
    0.06
    異
    0.06
    Act Density 0.203%

    No Known Activations