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

    Neuronpedia

    INDEX
    Explanations

    content creation/writing

    np_max-act · gemini-2.0-flash

    The neuron detects nouns and adjectives that describe product or service features, use cases, and purposes (e.g. marketing, design, customization, platform capabilities).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ylim
    -0.07
    Tuple
    -0.06
    _TRANSACTION
    -0.06
    ولد
    -0.06
    ($"{
    -0.06
    	edit
    -0.06
     believers
    -0.06
     Universities
    -0.06
     highlight
    -0.06
     Gust
    -0.06
    POSITIVE LOGITS
     forensic
    0.07
    ั้
    0.07
    ізнес
    0.07
    #ab
    0.07
     đặc
    0.06
    刻
    0.06
    ượng
    0.06
    버
    0.06
     upwards
    0.06
    mor
    0.06
    Act Density 0.040%

    No Known Activations