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

    Neuronpedia

    INDEX
    Explanations

    repetitive mentions of the word "in" and phrases that suggest belief or conviction

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

    believe in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Domínguez
    -0.45
    Première
    -0.43
    gelopen
    -0.40
     aparentemente
    -0.40
     deberes
    -0.39
    gasse
    -0.38
    queries
    -0.38
    Gateway
    -0.38
     recientemente
    -0.37
     nieuws
    -0.37
    POSITIVE LOGITS
    withIdentifier
    0.80
     Autorizaciones
    0.71
    tagHelperRunner
    0.70
     propOrder
    0.68
    IndentedString
    0.68
    ंदीखरीदारी
    0.67
    GEBURTSDATUM
    0.67
     дописавши
    0.66
    AnchorStyles
    0.65
    ValueStyle
    0.65
    Act Density 0.005%

    No Known Activations