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

    Neuronpedia

    INDEX
    Explanations

    Companies and technology

    np_max-act · gemini-2.0-flash

    The neuron activates on capitalized named entities—titles, brand or organization names, and other proper nouns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     spot
    -0.06
    Year
    -0.06
     shielding
    -0.06
    croft
    -0.06
     Consort
    -0.06
     -------↵
    -0.06
    obile
    -0.06
     куль
    -0.06
    PCP
    -0.06
     pix
    -0.06
    POSITIVE LOGITS
    -supported
    0.07
     NEVER
    0.07
    Sometimes
    0.07
    gregar
    0.07
     FAILED
    0.07
     GetLastError
    0.06
     Leads
    0.06
    Yet
    0.06
     lidé
    0.06
    Something
    0.06
    Act Density 0.103%

    No Known Activations