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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    This neuron activates on second-person address (you/your/need) and reader-directed instructions or imperatives.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ids
    -0.06
    _pedido
    -0.06
     militants
    -0.06
    'я
    -0.06
    .sin
    -0.06
    .data
    -0.06
    Inputs
    -0.06
     question
    -0.06
    vergence
    -0.06
    $count
    -0.06
    POSITIVE LOGITS
    byterian
    0.07
     enlarg
    0.07
    %A
    0.07
    ourg
    0.06
    妇
    0.06
    -moving
    0.06
     к
    0.06
    acyj
    0.06
    天天
    0.06
     purse
    0.06
    Act Density 0.093%

    No Known Activations