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

    Neuronpedia

    INDEX
    Explanations

    references to patent numbers and related identification details

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

    U.S. patent filed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orilla
    -0.35
    似
    -0.33
    Étape
    -0.32
    richten
    -0.32
    return
    -0.31
    ↵↵↵
    -0.30
     Propiedad
    -0.30
     dwell
    -0.29
     either
    -0.28
    llu
    -0.28
    POSITIVE LOGITS
    下载附件
    0.63
    ftagPool
    0.63
    RegistryLite
    0.63
    IndentedString
    0.60
    msgTypes
    0.59
     $_"
    0.58
     ujednoznacz
    0.58
    SBATCH
    0.57
    newtheorem
    0.57
    sidemargin
    0.56
    Act Density 0.150%

    No Known Activations