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

    Neuronpedia

    INDEX
    Explanations

    Code and databases

    np_max-act · gemini-2.0-flash

    The neuron detects SQL schema and data-definition content—sections that define, show, or modify table structures and related metadata.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     passes
    -0.07
     services
    -0.06
    ωσε
    -0.06
     subscribing
    -0.06
    /Image
    -0.06
     adults
    -0.06
    -photo
    -0.06
     EVERY
    -0.06
    会社
    -0.06
     shattered
    -0.06
    POSITIVE LOGITS
    eventName
    0.07
    增
    0.07
    aptop
    0.07
    Tai
    0.06
    IBM
    0.06
    MAC
    0.06
    ]:↵↵↵
    0.06
     Venus
    0.06
    _ALLOW
    0.06
    offee
    0.06
    Act Density 0.000%

    No Known Activations