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

    Neuronpedia

    INDEX
    Explanations

    code configuration files

    np_max-act · gemini-2.0-flash

    This neuron activates on schema or configuration field names (i.e. the keys in JSON, XML, protobuf, or similar structured-data definitions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Programming
    -0.07
    úmer
    -0.07
    (dot
    -0.07
    >ID
    -0.07
     super
    -0.07
    =admin
    -0.07
    -0.07
     kata
    -0.06
     contr
    -0.06
     zaměst
    -0.06
    POSITIVE LOGITS
    キング
    0.06
    exas
    0.06
    ette
    0.06
    educt
    0.06
    身上
    0.06
     Streaming
    0.06
     '')
    0.06
    rysler
    0.06
     голова
    0.06
     RaycastHit
    0.06
    Act Density 0.052%

    No Known Activations