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

    Neuronpedia

    INDEX
    Explanations

    unique

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot schema‐definition option keywords (like “required,” “index,” “unique,” “dropDups,” “true,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    文字
    -0.06
     berlin
    -0.06
     nama
    -0.06
     показ
    -0.06
     radians
    -0.06
    Six
    -0.06
    师
    -0.06
     spark
    -0.06
     br
    -0.06
     مرک
    -0.06
    POSITIVE LOGITS
    mia
    0.07
    ounters
    0.07
    lanmış
    0.07
    TV
    0.06
    кта
    0.06
    达到
    0.06
    .OPEN
    0.06
    (mutex
    0.06
    .Flat
    0.06
     trafficking
    0.06
    Act Density 0.003%

    No Known Activations