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

    Neuronpedia

    INDEX
    Explanations

    interface

    np_max-act · gemini-2.0-flash

    The neuron lights up on longer, multisyllabic “fancy” words—especially Latinate or technical terms (e.g. interface, analgesic, real-time, experience).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    content related to technological advancements and social critiques.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nay
    -0.07
     �
    -0.07
     إلا
    -0.07
    -fed
    -0.07
     Zinc
    -0.06
    qed
    -0.06
    خواست
    -0.06
     streak
    -0.06
    /fire
    -0.06
     رأ
    -0.06
    POSITIVE LOGITS
     дії
    0.06
     ende
    0.06
     targets
    0.06
    558
    0.06
     FEATURE
    0.06
     прем
    0.06
    .NewLine
    0.06
    EndInit
    0.05
    LOGY
    0.05
     være
    0.05
    Act Density 0.354%

    No Known Activations