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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of database tables (table names and related schema terms) in code or text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mát
    -0.07
    anni
    -0.07
    ограм
    -0.07
     校
    -0.06
     acre
    -0.06
     Past
    -0.06
     CMS
    -0.06
     बड़
    -0.06
     past
    -0.06
     College
    -0.06
    POSITIVE LOGITS
    /my
    0.07
    awei
    0.06
     Operators
    0.06
    />\
    0.06
    яем
    0.06
     druh
    0.06
     Personal
    0.06
    /tutorial
    0.06
     doch
    0.06
    \System
    0.06
    Act Density 0.107%

    No Known Activations