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

    Neuronpedia

    INDEX
    Explanations

    help or resources

    np_max-act · gemini-2.0-flash

    discussions about programming concepts and syntax.

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

    The neuron fires on phrasing that asks for pointers or references to external information or resources (e.g. “refer me,” “point me to,” “information on”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     สำ
    -0.07
     sticking
    -0.07
     alone
    -0.07
     Nh
    -0.07
    xz
    -0.06
     vener
    -0.06
    estatus
    -0.06
     WAR
    -0.06
    ﺮ
    -0.06
     ces
    -0.06
    POSITIVE LOGITS
    Tesla
    0.07
    modification
    0.07
     miễn
    0.06
    opo
    0.06
     ctrl
    0.06
    uly
    0.06
     hypo
    0.06
     Pax
    0.06
     deset
    0.06
     Irr
    0.06
    Act Density 0.017%

    No Known Activations