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

    Neuronpedia

    INDEX
    Explanations

    diverse topics

    np_max-act · gemini-2.0-flash

    This neuron activates on substantive nouns—especially longer, content-carrying terms—highlighting key topic words in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    OTS
    -0.07
    سم
    -0.07
    득
    -0.07
     mnoha
    -0.06
    azi
    -0.06
     Greatest
    -0.06
     Scope
    -0.06
    hots
    -0.06
    irical
    -0.06
     стен
    -0.06
    POSITIVE LOGITS
     nitel
    0.07
     �
    0.06
    953
    0.06
     gonna
    0.06
    (property
    0.06
    �
    0.06
    .ToArray
    0.06
     dividing
    0.06
     >>
    0.06
     paycheck
    0.06
    Act Density 0.109%

    No Known Activations