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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron fires on chunks of SQL (and SQL‐like) code, i.e. segments containing SQL keywords and queries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    했
    -0.07
    Lewis
    -0.07
    Fear
    -0.07
    이었다
    -0.07
    fad
    -0.06
    oje
    -0.06
    ΙΔ
    -0.06
    reative
    -0.06
    oystick
    -0.06
     спрос
    -0.06
    POSITIVE LOGITS
    xico
    0.06
    _inp
    0.06
     Sci
    0.06
     알아
    0.06
     Modifications
    0.06
    존
    0.06
    monthly
    0.06
    >');
    0.06
     формы
    0.06
    /A
    0.06
    Act Density 0.010%

    No Known Activations