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

    Neuronpedia

    INDEX
    Explanations

    nouns and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DDoS
    0.39
     GPU
    0.36
     malware
    0.35
     UEFI
    0.35
     FPGA
    0.34
     MIUI
    0.34
     configurable
    0.34
     Linux
    0.33
     मल्टी
    0.32
     Kubernetes
    0.32
    POSITIVE LOGITS
    Noun
    0.40
     /ˈ
    0.38
     noun
    0.37
     adjective
    0.37
     nouns
    0.36
     adverb
    0.35
    词
    0.34
     synonyms
    0.34
    noun
    0.33
    nouns
    0.33
    Act Density 1.430%

    No Known Activations