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

    Neuronpedia

    INDEX
    Explanations

    protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protection
    -2.11
     Protection
    -2.00
    protection
    -1.95
    Protection
    -1.86
     PROTECTION
    -1.76
     protecting
    -1.55
     protected
    -1.54
     protective
    -1.54
     protec
    -1.50
     protections
    -1.49
    POSITIVE LOGITS
    Personendaten
    1.03
    IUrlHelper
    0.86
    IntoConstraints
    0.81
     насељу
    0.81
     ProtoMessage
    0.77
     BoxDecoration
    0.77
    SharedDtor
    0.76
     intptr
    0.75
     समीक्षाओं
    0.75
     الرياضيه
    0.74
    Act Density 1.478%

    No Known Activations