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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotions and sentiments

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

    expressions of surprise or strong emotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kanpo
    -0.40
    Aholisi
    -0.40
    modelBuilder
    -0.36
     problems
    -0.34
    /******/
    -0.34
    DrawerToggle
    -0.33
    HasAnnotation
    -0.33
    ISSIPPI
    -0.32
    Casi
    -0.32
    GoogleApiClient
    -0.31
    POSITIVE LOGITS
     autorytatywna
    0.58
    ArgumentParser
    0.55
    ArgsConstructor
    0.54
     ModelExpression
    0.54
    ✨:
    0.52
    出版年
    0.52
    Bakgrunnsstoff
    0.51
    tvguidetime
    0.51
     فريبيس
    0.51
    ToBounds
    0.51
    Act Density 0.032%

    No Known Activations