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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of software lineage—phrases describing one project as “based on,” “built from,” or using another project’s source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .med
    -0.07
    _BAL
    -0.06
     Coil
    -0.06
    /menu
    -0.06
    ogan
    -0.06
     prem
    -0.06
     Milo
    -0.06
     SHR
    -0.06
    elapsed
    -0.06
     medi
    -0.06
    POSITIVE LOGITS
    connector
    0.07
    ��
    0.06
    亲
    0.06
     liken
    0.06
     nå
    0.06
    .getById
    0.06
    	rd
    0.06
    ضر
    0.06
    \Carbon
    0.06
     применения
    0.06
    Act Density 0.031%

    No Known Activations