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

    Neuronpedia

    INDEX
    Explanations

    passive voice

    np_max-act · gemini-2.0-flash

    references to scientific processes and mechanisms involving external fields and their interactions with atomic or molecular structures.

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

    This neuron fires on phrasing that signals a paper’s key contribution or methodological purpose (e.g. “provides the basis of a sensitive … mechanism”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    QB
    -0.07
    ализации
    -0.06
    _FROM
    -0.06
    وری
    -0.06
     Highland
    -0.06
     initiator
    -0.06
     Wonderland
    -0.06
     Slave
    -0.06
    ]._
    -0.06
     wo
    -0.06
    POSITIVE LOGITS
    فع
    0.07
     jars
    0.06
    ुपए
    0.06
    ناء
    0.06
     semua
    0.06
    ypress
    0.06
    Standard
    0.06
    roles
    0.06
    draul
    0.06
    нул
    0.06
    Act Density 0.078%

    No Known Activations