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

    Neuronpedia

    INDEX
    Explanations

    questions that express uncertainty or a need for guidance

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

    foreign language personal prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.56
     BoxDecoration
    -0.50
    ibrator
    -0.50
    ImageContext
    -0.48
     informée
    -0.47
    extAlignment
    -0.47
    HtmlAttribute
    -0.46
    makeText
    -0.46
    felizmente
    -0.46
    createStatement
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.45
     potrzebu
    0.42
     desire
    0.40
    writeFieldEnd
    0.40
     '{@
    0.39
    Personendaten
    0.39
     désir
    0.38
     @"/
    0.37
     ligiloj
    0.36
     yourself
    0.35
    Act Density 0.013%

    No Known Activations