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

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash

    concepts and discussions related to socialization and social networks.

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

    The neuron flags text written in Cyrillic script (e.g. Russian words).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     баз
    -0.07
    my
    -0.07
     experiments
    -0.07
     nm
    -0.07
     Override
    -0.06
    Secondary
    -0.06
     deliveries
    -0.06
    i
    -0.06
     ery
    -0.06
     Web
    -0.06
    POSITIVE LOGITS
    ença
    0.07
    少
    0.07
     number
    0.06
     several
    0.06
    babel
    0.06
     Mehr
    0.06
     кіль
    0.06
     �
    0.06
    inx
    0.06
    +=
    0.06
    Act Density 0.037%

    No Known Activations