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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    The neuron fires on the “(C)” copyright marker in code comments, effectively detecting copyright/license header lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    irty
    -0.06
     gallery
    -0.06
     〈
    -0.06
    作品
    -0.06
    itor
    -0.06
    iton
    -0.06
     panicked
    -0.06
    ुमत
    -0.06
    Restore
    -0.06
     Celtic
    -0.05
    POSITIVE LOGITS
     somebody
    0.07
    寒
    0.06
    employed
    0.06
     비
    0.06
    strand
    0.06
     QMainWindow
    0.06
     fend
    0.06
     dads
    0.06
     forIndexPath
    0.06
    (encoded
    0.06
    Act Density 0.001%

    No Known Activations