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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    specific SQL table definitions and related commands.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the scale specification (the second number) in numeric type definitions (e.g. the “2” in NUMERIC(10,2)).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ...\
    -0.07
     filles
    -0.07
     pause
    -0.07
    }".
    -0.07
     Pause
    -0.07
    -Ch
    -0.06
    cade
    -0.06
    manage
    -0.06
    eleri
    -0.06
    _successful
    -0.06
    POSITIVE LOGITS
     void
    0.07
    /find
    0.06
     Events
    0.06
     chemicals
    0.06
     мон
    0.06
     Thousands
    0.06
     Lens
    0.06
     posY
    0.06
     зак
    0.06
     internal
    0.06
    Act Density 0.019%

    No Known Activations