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

    Neuronpedia

    INDEX
    Explanations

    Mercedes

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the Mercedes-Benz brand name.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    意义
    -0.06
    -buffer
    -0.06
    _RANDOM
    -0.06
     '/',↵
    -0.06
    .Deep
    -0.06
     voxel
    -0.06
    _Ch
    -0.06
    Warnings
    -0.06
     Вол
    -0.06
    áticas
    -0.06
    POSITIVE LOGITS
     BMW
    0.09
     Mercedes
    0.09
    цуз
    0.07
     enables
    0.07
    -Benz
    0.07
     submit
    0.06
     authorize
    0.06
     olacağ
    0.06
     Volvo
    0.06
     φω
    0.06
    Act Density 0.003%

    No Known Activations