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

    Neuronpedia

    INDEX
    Explanations

    reading or scanning input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anting
    0.43
     बॉबी
    0.41
    Investor
    0.40
    ARTA
    0.39
    कृपया
    0.38
     মহল
    0.38
     उर्वशी
    0.38
    atha
    0.38
    Panoramic
    0.38
    arth
    0.37
    POSITIVE LOGITS
     Scan
    0.66
     scan
    0.65
    扫描
    0.57
     SCAN
    0.56
     Scanning
    0.55
    Scanning
    0.55
     scanning
    0.53
     scanned
    0.52
    scan
    0.52
    Scan
    0.52
    Act Density 0.002%

    No Known Activations