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

    Neuronpedia

    INDEX
    Explanations

    deficiency

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of tax deficiency amounts, specifically the word “deficiency” together with its associated dollar figure.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     人
    -0.07
    ?>>
    -0.07
    amarin
    -0.06
     fireEvent
    -0.06
    ΜΑΤ
    -0.06
     -*-
↵
    -0.06
    Lng
    -0.06
    (Util
    -0.06
    Mana
    -0.06
     ===>
    -0.06
    POSITIVE LOGITS
    �
    0.07
     ศ
    0.07
    ُم
    0.06
    Study
    0.06
     seeking
    0.06
    変更
    0.06
    109
    0.06
     surg
    0.06
     antes
    0.06
     пять
    0.06
    Act Density 0.000%

    No Known Activations