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

    Neuronpedia

    INDEX
    Explanations

    keywords related to testing or experiments in a programming or scientific context

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

    test methods and templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.31
    parsedMessage
    -1.17
    windowFixed
    -1.04
     Италијани
    -1.03
     kasarigan
    -1.03
     Geſch
    -0.98
     indígen
    -0.97
     wikipagina
    -0.97
     мәкал
    -0.97
     Biôgrafia
    -0.97
    POSITIVE LOGITS
     test
    0.40
    ↵
    0.39
    Test
    0.39
    ,
    0.38
     
    0.37
     Tuesday
    0.37
     Test
    0.36
     Sunday
    0.34
     Monday
    0.34
     Wednesday
    0.33
    Act Density 0.001%

    No Known Activations