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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    This neuron identifies SQL join clauses—specifically the JOIN and ON keywords in queries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fn
    -0.07
     محاس
    -0.07
     отп
    -0.07
    アイ
    -0.07
    pcf
    -0.07
     UIFont
    -0.06
    _integer
    -0.06
     팬
    -0.06
     tissues
    -0.06
    jejer
    -0.06
    POSITIVE LOGITS
    (mu
    0.06
     decisive
    0.06
     했
    0.06
     Domin
    0.06
     ro
    0.06
     konus
    0.06
    visual
    0.06
    Rod
    0.06
    From
    0.06
     discriminate
    0.06
    Act Density 0.009%

    No Known Activations