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

    Neuronpedia

    INDEX
    Explanations

    numerical values and various codes or identifiers

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

    values inside parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.76
    出版年
    -0.74
    ########.
    -0.65
     defaultstate
    -0.61
     surla
    -0.59
     autorytatywna
    -0.58
     '\\;'
    -0.58
    @[+][
    -0.57
     AssemblyCulture
    -0.56
    UserScript
    -0.56
    POSITIVE LOGITS
    XmlAccessorType
    0.42
     navideña
    0.40
     compagnon
    0.38
    essentiel
    0.38
     suprême
    0.38
     doigt
    0.36
     dupla
    0.36
     coupable
    0.36
     cuenca
    0.35
    again
    0.35
    Act Density 0.016%

    No Known Activations