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

    Neuronpedia

    INDEX
    Explanations

    Code and database queries

    np_max-act · gemini-2.0-flash

    This neuron detects references to “id” columns in SQL queries (especially occurrences of `.id`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gy
    -0.07
     SECOND
    -0.07
    리의
    -0.06
     Pest
    -0.06
    _ORDER
    -0.06
     Months
    -0.06
     Lans
    -0.06
     bereits
    -0.06
     Believe
    -0.06
     Rage
    -0.06
    POSITIVE LOGITS
     beste
    0.06
     {/*
    0.06
    allel
    0.06
    ?q
    0.06
     declaring
    0.06
    曜日
    0.06
    θεν
    0.06
     방법
    0.06
    cling
    0.06
     продук
    0.06
    Act Density 0.012%

    No Known Activations