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

    Neuronpedia

    INDEX
    Explanations

    specific

    np_max-act · gemini-2.0-flash

    requests for specific information or queries regarding recent events or topics.

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

    The neuron flags terms that refer to particular, detailed information—words like “specific,” “information,” “data,” or “events.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unravel
    -0.07
    久久
    -0.07
    ımızda
    -0.06
    _lb
    -0.06
     сделать
    -0.06
    ając
    -0.06
     chocolates
    -0.06
    smart
    -0.06
    教师
    -0.06
    ları
    -0.06
    POSITIVE LOGITS
    je
    0.06
    _LOAD
    0.06
    quisites
    0.06
    _mentions
    0.06
     DEST
    0.06
     Phill
    0.06
    0.06
    .SelectedItems
    0.05
    �
    0.05
     다음
    0.05
    Act Density 0.019%
    No Known Activations