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

    Neuronpedia

    INDEX
    Explanations

    marker

    np_max-act · gemini-2.0-flash

    This neuron detects the term “marker” (often in phrases like “marker of” or “marker for”), signaling discussion of biomarkers or diagnostic indicators.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Geoff
    -0.07
    isations
    -0.06
     ScrollView
    -0.06
     Wash
    -0.06
     Administrative
    -0.06
     deviations
    -0.06
     αφ
    -0.06
    840
    -0.06
    อฟ
    -0.06
    445
    -0.06
    POSITIVE LOGITS
     markers
    0.08
     marker
    0.08
     tracer
    0.07
    AR
    0.07
     MARK
    0.07
    er
    0.07
    marker
    0.07
     docker
    0.07
     targeted
    0.07
     source
    0.07
    Act Density 0.007%

    No Known Activations