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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash

    The neuron activates on URL fragments—especially the “://” protocol marker and adjoining URL characters.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    MARK
    -0.07
    DEPEND
    -0.07
     RCS
    -0.07
    pdata
    -0.06
     dwind
    -0.06
    -cmpr
    -0.06
    anco
    -0.06
    ripper
    -0.06
     McCabe
    -0.06
     المهنة
    -0.06
    POSITIVE LOGITS
     Pty
    0.06
     Obl
    0.06
     sessionId
    0.06
     gratuites
    0.06
     lastIndex
    0.06
     tournaments
    0.06
     warranties
    0.06
     grate
    0.06
    (namespace
    0.06
    routes
    0.06
    Act Density 0.008%

    No Known Activations