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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron fires on object‐property identifiers—especially the common task fields like “id,” “description,” “completed,” and “total.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ourcing
    -0.07
    �
    -0.07
    灰
    -0.07
    Breadcrumb
    -0.06
    .Id
    -0.06
     vascular
    -0.06
    Heading
    -0.06
     bunny
    -0.06
    otty
    -0.06
     prisons
    -0.06
    POSITIVE LOGITS
     поможет
    0.06
    .Tables
    0.06
     Daly
    0.06
    -caret
    0.06
    ーリ
    0.06
    _sep
    0.06
    _add
    0.06
    etas
    0.06
    \
    0.06
    _LONG
    0.06
    Act Density 0.145%

    No Known Activations