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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology

    np_max-act · gemini-2.0-flash

    unique structural characteristics of viral proteins.

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

    This neuron fires on scientific or technical entity names—proper nouns, acronyms, and formula‐style terms (e.g. disease names, element symbols, H II regions, blazars, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _sb
    -0.07
    แ
    -0.06
    azz
    -0.06
    brahim
    -0.06
     обеспе
    -0.06
    �
    -0.06
    前往
    -0.06
    мя
    -0.06
    /helper
    -0.06
    /rc
    -0.06
    POSITIVE LOGITS
    =X
    0.07
     INTO
    0.06
    DialogContent
    0.06
    .dropdown
    0.06
    霊
    0.06
     Xiaomi
    0.06
     دارند
    0.06
     kent
    0.06
    uction
    0.06
    perms
    0.06
    Act Density 0.040%

    No Known Activations