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

    Neuronpedia

    INDEX
    Explanations

    law citations and legal documents

    oai_token-act-pair · gemini-2.0-flash

    Legal/policy documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.72
    ########.
    -0.67
    RectangleBorder
    -0.65
    expandindo
    -0.63
     متعلقه
    -0.58
     Paglinawan
    -0.58
     ModelExpression
    -0.56
     Италијани
    -0.54
     Dernière
    -0.54
    IndentedString
    -0.54
    POSITIVE LOGITS
     ✭✭
    0.56
     getItemCount
    0.52
     VIAF
    0.52
    EndProject
    0.51
     imper
    0.50
    istung
    0.48
    ارض
    0.48
     appré
    0.47
    batore
    0.47
    maquilla
    0.47
    Act Density 2.007%

    No Known Activations