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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.86
     nahilalakip
    -0.84
     EconPapers
    -0.78
     Efq
    -0.78
    fourths
    -0.74
    migrationBuilder
    -0.73
    клопе
    -0.73
     Avenue
    -0.73
    IsPostBack
    -0.73
     kasarigan
    -0.71
    POSITIVE LOGITS
    ly
    0.69
    er
    0.69
    ably
    0.60
    y
    0.58
    ی
    0.58
    able
    0.57
    dy
    0.56
    ed
    0.55
    ry
    0.55
    ing
    0.55
    Act Density 0.481%

    No Known Activations