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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash

    This neuron fires on self-referential promotional language—mentions of the program or organization’s own name, “we/our,” and direct calls to action like “contact us” or “let us know.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _SET
    -0.07
    Generator
    -0.07
    PARSE
    -0.07
    ppard
    -0.06
     epsilon
    -0.06
    istani
    -0.06
    LIKELY
    -0.06
    IsRequired
    -0.06
     Shared
    -0.06
     Sinh
    -0.06
    POSITIVE LOGITS
     {↵↵↵↵
    0.08
     збір
    0.07
    {↵↵↵
    0.07
     =>{↵
    0.07
    ;
↵
↵
↵
    0.06
    );
↵
↵
↵
    0.06
     //
↵
↵
    0.06
    (coll
    0.06
    toHave
    0.06
    "}}>↵
    0.06
    Act Density 0.061%

    No Known Activations