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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word "Mathematics," as used in headings like subject classifications or institutional affiliations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	trans
    -0.06
    encoder
    -0.06
    (ed
    -0.06
    bow
    -0.06
    Pt
    -0.06
    _Render
    -0.06
     pragmatic
    -0.06
     GT
    -0.06
     ==>
    -0.06
     bert
    -0.06
    POSITIVE LOGITS
    >Edit
    0.07
     instituted
    0.07
     sling
    0.07
    插
    0.06
     courts
    0.06
     knew
    0.06
     мік
    0.06
    수로
    0.06
    -art
    0.06
     court
    0.06
    Act Density 0.007%

    No Known Activations