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

    Neuronpedia

    INDEX
    Explanations

    email address patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    citations and special identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ператор
    -0.45
    лтемелер
    -0.41
     esercit
    -0.38
    ]),
    -0.37
     exercice
    -0.35
    있
    -0.35
    ]]
    -0.35
     exercise
    -0.34
     싶
    -0.34
    '])
    -0.33
    POSITIVE LOGITS
     '@
    1.89
    ("@
    1.64
     "@
    1.55
    "@
    1.48
    ('@
    1.31
    '@
    1.24
    ="@
    1.01
     @{
    0.90
     '@/
    0.89
     "@/
    0.84
    Act Density 0.146%

    No Known Activations