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

    Neuronpedia

    INDEX
    Explanations

    relational

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of relational/SQL database concepts and terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     attic
    -0.07
    .start
    -0.07
    不会
    -0.06
    ching
    -0.06
    [].
    -0.06
     dostate
    -0.06
    *.
    -0.06
    ARGE
    -0.06
    elve
    -0.06
    /ion
    -0.06
    POSITIVE LOGITS
    ]))↵
    0.07
     Midwest
    0.07
    .orm
    0.07
    noDB
    0.07
     halfway
    0.07
     stagnant
    0.06
    ผม
    0.06
    gregar
    0.06
    flamm
    0.06
    нож
    0.06
    Act Density 0.005%

    No Known Activations