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

    Neuronpedia

    INDEX
    Explanations

    words and phrases denoting good and bad with respect to health, morality, and/or choices

    oai_token-act-pair · gemini-2.0-flash

    health and morality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reverso
    -0.54
    TagMode
    -0.53
    HtmlAttribute
    -0.52
    resizingMask
    -0.52
    WithIOException
    -0.50
    -0.50
    ignes
    -0.49
    IsContent
    -0.49
     surla
    -0.48
    __":
    -0.47
    POSITIVE LOGITS
     nimic
    0.71
    GOTREF
    0.63
    ſelf
    0.58
     myſelf
    0.56
     uſed
    0.55
     CKD
    0.55
     textStatus
    0.55
     uſe
    0.54
     Allociné
    0.54
     pleaſure
    0.54
    Act Density 2.842%

    No Known Activations