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

    Neuronpedia

    INDEX
    Explanations

    Travel and transit

    np_max-act · gemini-2.0-flash

    The neuron detects first-person statements of personal actions or activities (e.g. “I take a weekend morning walk”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Depot
    -0.06
     لذا
    -0.06
    _pow
    -0.06
     เล
    -0.05
     Fruit
    -0.05
     škol
    -0.05
     recourse
    -0.05
    UFFIX
    -0.05
     pager
    -0.05
     dışında
    -0.05
    POSITIVE LOGITS
    systems
    0.07
    รง
    0.07
    istrates
    0.07
    reich
    0.07
    lider
    0.07
    hani
    0.07
    acts
    0.07
    ओ
    0.07
     Constructors
    0.07
    _Min
    0.06
    Act Density 0.043%

    No Known Activations