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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects formal legislative mandate language—i.e. words that specify required actions or directives (like “require,” “direct,” “establish,” “policy,” etc.) in a bill or regulation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    甜
    -0.06
    letes
    -0.06
    [result
    -0.06
    .list
    -0.06
    .Selected
    -0.06
    IX
    -0.06
    特別
    -0.06
     AdapterView
    -0.06
     abortion
    -0.06
    _dataset
    -0.06
    POSITIVE LOGITS
    protected
    0.07
    	glm
    0.06
    RenderWindow
    0.06
     अप
    0.06
     वह
    0.06
    uster
    0.06
     uart
    0.06
     sd
    0.06
     equally
    0.06
     UINT
    0.06
    Act Density 0.037%

    No Known Activations