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

    Neuronpedia

    INDEX
    Explanations

    references to problems, investigations, and the process of addressing issues

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

    break down or declared incident

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enseñanza
    -0.31
     popularidad
    -0.30
    เค้า
    -0.27
    phylla
    -0.27
     passione
    -0.27
     passion
    -0.27
    很多的
    -0.26
    uli
    -0.25
     desej
    -0.24
    CreateModel
    -0.24
    POSITIVE LOGITS
    RegressionTest
    0.70
    ThroughAttribute
    0.70
     OFDb
    0.69
     }{@
    0.61
    SequentialGroup
    0.60
    0.59
     disambiguazione
    0.59
    !*\
    0.58
     NSCoder
    0.57
    emergency
    0.57
    Act Density 0.017%

    No Known Activations