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

    Neuronpedia

    INDEX
    Explanations

    connections and transitions in arguments or statements

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

    "and therefore", "and these", or "and may"

    np_acts-logits-general · gemini-2.0-flash

    and then a connector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Erreferentziak
    -0.69
     AssemblyCulture
    -0.65
     quoique
    -0.59
    </caption>
    -0.59
    팎
    -0.55
    Answered
    -0.54
    AxisAlignment
    -0.54
     tanya
    -0.54
     pinulongan
    -0.52
     certes
    -0.52
    POSITIVE LOGITS
    WEBPACK
    0.62
     they
    0.62
     بيها
    0.61
    这也是
    0.60
     thereby
    0.58
     nahilalakip
    0.57
     there
    0.56
    esez
    0.55
     հղումներ
    0.55
    __':
    0.55
    Act Density 0.696%

    No Known Activations