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

    Neuronpedia

    INDEX
    Explanations

    OSINT email harvesting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Database
    0.60
     database
    0.59
    Database
    0.58
     查询
    0.58
    database
    0.57
    查询
    0.57
     checking
    0.55
    查詢
    0.55
     databases
    0.54
     querying
    0.54
    POSITIVE LOGITS
    Photos
    0.49
    Relatives
    0.47
     relatives
    0.43
     Photos
    0.43
    photos
    0.43
     fotos
    0.40
     photos
    0.39
    associated
    0.37
    Fotos
    0.36
     fot
    0.35
    Act Density 0.005%

    No Known Activations