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

    Neuronpedia

    INDEX
    Explanations

    instructions or recommendations related to crediting sources

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

    credit or label text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mu
    -0.43
    poor
    -0.37
    my
    -0.34
    cha
    -0.33
    e
    -0.33
    db
    -0.32
     poor
    -0.32
    imli
    -0.32
     Poor
    -0.31
    はじめに
    -0.31
    POSITIVE LOGITS
     Италијани
    0.75
     nahilalakip
    0.73
     CanadaChoose
    0.71
     estekak
    0.66
     Vikipedi
    0.64
     <<<<<<<<<<<<<<
    0.64
     pinulongan
    0.63
     lenker
    0.61
    KommentareTeilen
    0.59
    تقاوى
    0.58
    Act Density 0.001%

    No Known Activations