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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash

    The neuron activates on column names when they’re listed as part of a PRIMARY KEY definition in SQL DDL statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     نوش
    -0.07
     Sanayi
    -0.07
     heterosexual
    -0.07
    imu
    -0.07
    자의
    -0.06
     getaway
    -0.06
     seminars
    -0.06
     biochemical
    -0.06
     понима
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Kn
    0.06
                                  ↵
    0.06
    .stack
    0.06
    _roll
    0.06
    ิเศษ
    0.06
    453
    0.06
    gra
    0.06
     Nodes
    0.06
    	Register
    0.06
                          ↵
    0.06
    Act Density 0.006%

    No Known Activations