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

    Neuronpedia

    INDEX
    Explanations

    ip addresses and network configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vorder
    0.61
     kl
    0.60
     Amtrak
    0.60
    힛
    0.58
     HTML
    0.58
     kon
    0.58
     implement
    0.56
     UD
    0.55
     AKS
    0.55
     CRT
    0.55
    POSITIVE LOGITS
    <mask>
    0.67
    ".*:
    0.62
    yer
    0.62
    wählen
    0.60
    xxx
    0.59
    \.
    0.58
    សិក
    0.57
    开头
    0.57
    ulières
    0.57
    ꗬ
    0.57
    Act Density 0.013%

    No Known Activations