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

    Neuronpedia

    INDEX
    Explanations

    words related to independence and distinctiveness

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

    preceding capital letters

    np_acts-logits-general · gemini-2.0-flash

    Lauren Sandler, Lanai, Frankfurt, France

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.66
     pinulongan
    -0.53
    AddTagHelper
    -0.52
     مشين
    -0.50
     дописавши
    -0.50
    ASONS
    -0.47
    -0.47
    findpost
    -0.46
    MigrationBuilder
    -0.45
    pares
    -0.44
    POSITIVE LOGITS
    "</
    0.58
    }}</
    0.57
    ,:);
    0.56
    Kapcsolódó
    0.55
     cing
    0.55
    .'</
    0.55
    zia
    0.54
    }</
    0.53
     }}</
    0.52
     Cabello
    0.52
    Act Density 0.135%

    No Known Activations