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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals, particularly last names

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

    names with uer/uen suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.55
    KindOfClass
    -0.50
    Tembelea
    -0.49
    AutoField
    -0.48
     propOrder
    -0.47
     disambiguazione
    -0.46
    flashdata
    -0.46
    См
    -0.45
    orghini
    -0.45
     Lightfoot
    -0.44
    POSITIVE LOGITS
    uer
    1.97
    uel
    1.83
    UER
    1.57
    UEL
    1.48
    ues
    1.41
    uen
    1.36
    UES
    1.21
    ued
    1.21
    uez
    1.13
    uers
    1.12
    Act Density 0.013%

    No Known Activations