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

    Neuronpedia

    INDEX
    Explanations

    scan

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the root “scan” (e.g. scan, scanning) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    PRIMARY
    -0.08
    iptables
    -0.08
    Pear
    -0.08
     hypert
    -0.07
     Gret
    -0.07
    يمة
    -0.07
    ourt
    -0.07
     Giles
    -0.07
    _partition
    -0.07
    TargetException
    -0.06
    POSITIVE LOGITS
     Scan
    0.14
     scan
    0.13
     scans
    0.13
    Scan
    0.11
    scan
    0.10
     scanning
    0.09
    cam
    0.09
     scanned
    0.09
     SCAN
    0.09
    SCAN
    0.09
    Act Density 0.009%

    No Known Activations