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

    Neuronpedia

    INDEX
    Explanations

    Biographies

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the relative pronoun “which” (marking subordinate clauses).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _algo
    -0.07
     glasses
    -0.07
     reading
    -0.06
     string
    -0.06
    80
    -0.06
    :{↵
    -0.06
     compounds
    -0.06
     stove
    -0.06
     Reading
    -0.06
     notes
    -0.06
    POSITIVE LOGITS
    _shortcode
    0.08
     Bản
    0.07
     Amit
    0.07
    .shtml
    0.07
    apanese
    0.06
     ime
    0.06
    _drvdata
    0.06
     QTest
    0.06
    
    0.06
    Todos
    0.06
    Act Density 0.064%

    No Known Activations