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

    Neuronpedia

    INDEX
    Explanations

    architecture details

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect references to architectural style and building‐feature terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Front
    -0.07
     Macros
    -0.07
     tiết
    -0.07
    _sms
    -0.06
     parks
    -0.06
     countered
    -0.06
     keine
    -0.06
     elo
    -0.06
    ».↵↵
    -0.06
    Nintendo
    -0.06
    POSITIVE LOGITS
    weit
    0.07
     futuro
    0.07
     aer
    0.06
    uster
    0.06
     Aeros
    0.06
     dolay
    0.06
    $("
    0.06
    \uC
    0.06
     côt
    0.06
    ’app
    0.06
    Act Density 0.011%

    No Known Activations