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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron detects scientific acronyms or abbreviations (typically all-uppercase letter sequences) often introduced or enclosed in parentheses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ============↵
    -0.07
     super
    -0.06
    76
    -0.06
    -category
    -0.06
    عن
    -0.06
     المح
    -0.06
    ¦
    -0.05
     "...
    -0.05
     màn
    -0.05
    -0.05
    POSITIVE LOGITS
     Auxiliary
    0.07
     Medieval
    0.07
    jm
    0.07
    _phrase
    0.07
    ensored
    0.06
     이를
    0.06
     Broadcom
    0.06
    <Employee
    0.06
    ник
    0.06
    _IMM
    0.06
    Act Density 0.072%

    No Known Activations