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

    Neuronpedia

    INDEX
    Explanations

    expressions related to human relationships and interactions

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

    object particles after nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.54
    tagHelperRunner
    -0.53
    Jeografia
    -0.52
    ✭✭
    -0.50
    apimachinery
    -0.48
    yntaxException
    -0.48
    >>();
    -0.47
     cuivre
    -0.44
    TagMode
    -0.44
    esModule
    -0.44
    POSITIVE LOGITS
     समीक्षाओं
    0.36
     beszél
    0.36
    gezogen
    0.35
     backyard
    0.35
    過來
    0.35
     speaking
    0.34
    explor
    0.34
    liai
    0.34
     Dys
    0.34
    來的
    0.34
    Act Density 0.015%

    No Known Activations