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

    Neuronpedia

    INDEX
    Explanations

    prestigious

    np_max-act · gemini-2.0-flash

    The neuron selectively detects the adjective “prestigious,” marking mentions of high-status or honorific contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sand
    -0.07
     mir
    -0.06
     Love
    -0.06
    -book
    -0.06
    -or
    -0.06
     comic
    -0.06
     Polynomial
    -0.06
     SIM
    -0.06
    WND
    -0.06
    eyond
    -0.06
    POSITIVE LOGITS
     prestigious
    0.14
     prestige
    0.11
     distinguished
    0.09
     Prest
    0.09
    тех
    0.08
     NEC
    0.07
    STONE
    0.07
    ::_('
    0.07
    istinguished
    0.07
    rest
    0.07
    Act Density 0.004%

    No Known Activations