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

    Neuronpedia

    INDEX
    Explanations

    businesses

    np_max-act · gemini-2.0-flash

    phrases related to local businesses and services.

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

    The neuron fires on self-referential, promotional language where a business talks about its own services or history (e.g. “We are a family-owned business serving… since…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ignore
    -0.08
    iagnostics
    -0.07
    Logical
    -0.07
    _ne
    -0.07
    _effect
    -0.06
    Transformation
    -0.06
    ishi
    -0.06
     Єв
    -0.06
     Rogue
    -0.06
    .AutoSizeMode
    -0.06
    POSITIVE LOGITS
     dout
    0.06
    (track
    0.06
    /terms
    0.06
     Blowjob
    0.06
    _TILE
    0.06
     податков
    0.06
     //</
    0.06
    ENSION
    0.06
    <=$
    0.06
     NETWORK
    0.06
    Act Density 0.058%

    No Known Activations