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

    Neuronpedia

    INDEX
    Explanations

    topics related to affirmative action and social justice issues

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

    social and political debates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anInt
    -0.39
    eckt
    -0.36
    aClass
    -0.36
    IRE
    -0.35
    ModelBuilder
    -0.35
     how
    -0.35
    rouw
    -0.34
    うま
    -0.34
    nyata
    -0.34
    間に
    -0.34
    POSITIVE LOGITS
    хьтан
    0.62
    IntoConstraints
    0.61
     Italijani
    0.60
    Diwedd
    0.56
    useNewUrlParser
    0.54
     CreateTagHelper
    0.53
     pinulongan
    0.51
    Билгалдахарш
    0.50
     Picchu
    0.50
    ̈́
    0.50
    Act Density 0.062%

    No Known Activations