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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash

    references to system parameters related to machine learning models.

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

    This neuron responds to passive‐voice auxiliary constructions (e.g. “is being asked”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     divider
    -0.07
    参加
    -0.07
    บก
    -0.07
     kontrol
    -0.06
    _InitStruct
    -0.06
     cihaz
    -0.06
     гол
    -0.06
    _helpers
    -0.06
    вроп
    -0.06
     fragmented
    -0.06
    POSITIVE LOGITS
    \API
    0.06
     Affordable
    0.06
    .getValueAt
    0.06
    stasy
    0.06
    보
    0.06
     Token
    0.06
    Navigation
    0.06
    ancement
    0.06
     Travel
    0.06
    éd
    0.06
    Act Density 0.018%

    No Known Activations