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

    Neuronpedia

    INDEX
    Explanations

    thank

    np_max-act · gemini-2.0-flash

    The neuron detects acknowledgments or thank‐you statements (expressions of gratitude/funding support) in academic texts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    神
    -0.07
    group
    -0.07
    rel
    -0.06
    .take
    -0.06
    nings
    -0.06
     reputation
    -0.06
     wheat
    -0.06
    JECTION
    -0.06
    -hook
    -0.06
     cases
    -0.06
    POSITIVE LOGITS
     znač
    0.07
     کارخانه
    0.07
     Spielberg
    0.07
    =\"#
    0.06
     XT
    0.06
     감독
    0.06
    lerdir
    0.06
    ProgressDialog
    0.06
    Acknowled
    0.06
    _Format
    0.06
    Act Density 0.003%

    No Known Activations