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

    Neuronpedia

    INDEX
    Explanations

    giving directions

    np_max-act · gemini-2.0-flash

    specific references to meeting arrangements and locations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Network
    -0.07
    algorithm
    -0.07
     website
    -0.06
    -0.06
    Increases
    -0.06
     ":
    -0.06
    (expr
    -0.06
     otherwise
    -0.06
    ductive
    -0.06
     Yo
    -0.06
    POSITIVE LOGITS
    边
    0.07
    _REST
    0.06
    phem
    0.06
    "/>
↵
    0.06
    Long
    0.06
    故事
    0.06
    ँ
    0.06
    ","");↵
    0.06
    avar
    0.06
    ующие
    0.06
    Act Density 0.036%

    No Known Activations