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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or relationships between subjects

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

    joining clauses or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idéia
    -0.29
    Cv
    -0.28
     skla
    -0.28
     link
    -0.27
     g
    -0.27
     swojej
    -0.26
     c
    -0.25
    </blockquote>
    -0.25
     effected
    -0.25
     täglichen
    -0.25
    POSITIVE LOGITS
     Савезне
    0.93
     kaarangay
    0.86
    évaluateur
    0.82
     allAfrica
    0.80
    parsedMessage
    0.78
     itſelf
    0.77
     Chwiliwch
    0.75
    tagHelperRunner
    0.70
     CURIAM
    0.68
    WriteTagHelper
    0.67
    Act Density 0.130%

    No Known Activations