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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and conflicts within relationships

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

    a period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.75
    Personensuche
    -0.75
     informée
    -0.71
     surla
    -0.69
    يكب
    -0.69
     nahilalakip
    -0.69
     MainAxisSize
    -0.68
    aarrggbb
    -0.67
    RuleContext
    -0.67
     disambiguazione
    -0.67
    POSITIVE LOGITS
    */].
    0.28
     critical
    0.25
    NotNil
    0.24
    TERS
    0.23
    ({
    0.21
    好了
    0.21
     selve
    0.21
    င
    0.21
    لينكات
    0.20
     uParam
    0.20
    Act Density 0.063%

    No Known Activations