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

    Neuronpedia

    INDEX
    Explanations

    threads

    np_max-act · gemini-2.0-flash

    This neuron fires on standalone title- or header-style keywords (often capitalized topic labels) such as “Job,” “Openings,” “Benchmark,” “Recruitment,” “Exhibition,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (drop
    -0.06
     BBB
    -0.06
     breast
    -0.06
     translations
    -0.06
    HttpGet
    -0.06
    隨
    -0.06
    (vals
    -0.06
    违
    -0.06
     Whip
    -0.06
     EFF
    -0.06
    POSITIVE LOGITS
     Utf
    0.07
     националь
    0.07
    kr
    0.06
    .temperature
    0.06
     Econ
    0.06
     Casinos
    0.06
    ;}
↵
    0.06
    aneously
    0.06
    hwnd
    0.06
    �
    0.06
    Act Density 0.378%

    No Known Activations